This directory is created automatically and some papers may be mislabeled. Only document within the CiteSeer database are listed. The directory is intended to provide entry points for browsing the database and is not intended to be authoritative. Papers may not appear in all relevant categories. For example, papers in a sub-category may not appear in higher level categories.
11585.2 Evolutionary Design of Neural Architectures - A Preliminary Taxonomy.. - Balakrishnan, Honavar (1995)(Correct)
This report briefly motivates current research on evolutionary design of neural
architectures (EDNA) and presents a short overview of major research issues in
this area. It also includes a preliminary... / Introduction Artificial neural networks Rumelhart McClelland br superficial to biological neural networks brains Despite much
8912.2 A Guide to the Literature on Learning Probabilistic Networks From Data - Buntine (1996)(Correct)
This literature review discusses different methods
under the general rubric of learning Bayesian networks
from data, and includes some overlapping work on more general
probabilistic networks. Connecti... / drawn between the statistical neural network and uncertainty communities br and to a lesser degree in neural networks where biological views offer
7937.9 A Comprehensive Review of Production-Oriented Manufacturing Cell.. - Joines, King, Culbreth (1996)(Correct)
This paper offers a comprehensive review and classification of techniques to manipulate
part routing sequences for manufacturing cell formation. Individual techniques
are aggregated into methodologica... / have used the artificial neural network back-propagation algorithm to br while Awwal used Hopfield neural networks. El Maraghy and Gu used
7653.4 Recurrent Multilayer Perceptrons for Identification and Control: The.. - K. Tutschku (1995)(Correct)
This study investigates the properties of artificial recurrent neural networks.
Particular attention is paid to the question of how these nets can be applied to the
identification and control of non... / of artificial recurrent neural networks. Particular attention is br approaches are required. Neural networks are considered to be useful
7387.5 A Framework for Programming Embedded Systems: Initial Design and.. - Thrun (1998)(Correct)
This paper describes CES, a proto-type of a new programming language for robots and other
embedded systems, equipped with sensors and actuators. CES contains two new ideas, currently
not found in othe... / system trained an artificial neural network to map camera images to br own work we recently employed neural networks for sensor interpretation and
7140.6 Learning with Graphical Models - Buntine (1994)(Correct)
Probabilistic graphical models are being used widely in artificial intelligence, for instance,
in diagnosis and expert systems, as a unified qualitative and quantitative framework for representing
and... / extended to machine learning neural networks knowledge discovery and br fields machine learning neural networks etc. Earlier introductions
7116.4 Symbolic Artificial Intelligence And Numeric Artificial Neural.. - Honavar (1994)(Correct)
This
memory can take several forms based on the time scales at which such modifications
are allowed. Some symbol structures might have the property of determining
choice and the order of application o... / And Numeric Artificial Neural Networks Towards A Resolution Of br SAI and numeric artificial neural networks NANN or connectionist
6842.1 Incorporating Information From Syllable-length Time Scales Into.. - Wu (1998)(Correct)
Incorporating the concept of the syllable into speech recognition may improve
recognition accuracy through the integration of information over syllable-length time
spans. Evidence from psychoacoustics... / . . Probability Estimation Neural Network br from an onset- detection neural network at frames covered by
6547.9 Speech Recognition using Neural Networks - Tebelskis (1995)(Correct)
This thesis examines how artificial neural networks can benefit a large vocabulary, speaker independent, continuous speech recognition system. Currently, most speech recognition systems are based on h... / Speech Recognition using Neural Networks Joe Tebelskis May br Keywords Speech recognition neural networks hidden Markov models hybrid
6191.8 Optimization and global minimization methods suitable for neural.. - Duch, Korczak (1998)(Correct)
Neural networks are usually trained using local, gradient-based procedures. Such methods frequently
find suboptimal solutions being trapped in local minima. Optimization of neural structures and globa... / methods suitable for neural networks Wl odzisl aw Duch and br Illkirch France Abstract Neural networks are usually trained using
6029.8 Speech Processing with Linear and Neural Network Models - Burrows (1996)(Correct)
ion,
for imposing continuity between models of adjacent speech segments, and learning rate
adaptation, for improving back-propagation training, are discussed. For synthesising real
speech utterances, ... / Processing with Linear and Neural Network Models Tina-Louise Burrows br models and single hidden layer neural networks. The study is divided into
6004.1 Probabilistic Analysis of Learning in Artificial Neural Networks: The .. - Anthony (1997)(Correct)
There are a number of mathematical approaches to the study of learning and generalization in
artificial neural networks. Here we survey the `probably approximately correct' (PAC) model
of learning and... / of Learning in Artificial Neural Networks The PAC Model and its br generalization in artificial neural networks. Here we survey the probably
5543.2 Computational Complexity Of Neural Networks: A Survey - Orponen (1995)(Correct)
We survey some of the central results in the complexity theory of discrete neural
networks, with pointers to the literature. Our main emphasis is on the computational
power of various acyclic and c... / Computational Complexity Of Neural Networks A Survey Pekka Orponen br complexity theory of discrete neural networks with pointers to the
5505.8 Analysis, Visualization and Meta-analysis of Functional Neuroimages.. - Nielsen (1999)(Correct)
New approaches in this thesis:
ffl Comparison of convolution models for fMRI time-series modelling
ffl Canonical Ridge Analysis applied to functional neuroimages
ffl Some kind of neuroinformatics
... / . . Articial neural networks . br . . Analyzing a neural network the saliency map .
5222.3 Minimal Simulations For Evolutionary Robotics - Jakobi (1998)(Correct)
this paper, the line is drawn between controller
and environment.
3.1.1 Drawing the line between controller and environment unknown Minimal Simulations For Evolutionary Robotics
Nick Jakobi
Submitted... / discusses the best types of neural network encoding scheme genetic br . . . Neural networks for evolutionary robotics .
5142.3 Neural networks for modelling and control - Ronco, Gawthrop (1997)(Correct)
This report is a review of the main neuro-control technologies. Two main kinds of neuro-control
approaches are distinguished. One entails developing a single controller from a neural network
and the o... / Neural networks for modelling and control br a single controller from a neural network and the other one embeds a
5075.7 Complements to 'Pattern Recognition and Neural Networks' - Ripley (1996)(Correct)
Introduction Page 4: The book by Przytula & Prasanna (1993) discusses in detail the parallel implementation of neural networks. Page 16: Langley (1996) provides a book-length introduction to one viewp... / to Pattern Recognition and Neural Networks' by B.D. Ripley br the parallel implementation of neural networks. Page Langley
5000.3 The Hippocampus And Cerebellum In Adaptively Timed Learning.. - Grossberg, Merrill (1995)(Correct)
The concepts of declarative memory and procedural memory have been used to distinguish
two basic types of learning. A neural network model suggests how such memory
processes work together as recogniti... / two basic types of learning. A neural network model suggests how such memory br rule was introduced into neural network models in Grossberg a
4998.5 Connectionist Theory Refinement: Genetically Searching the Space of.. - Opitz, al. (1997)(Correct)
An algorithm that learns from a set of examples should ideally be able to exploit the
available resources of (a) abundant computing power and (b) domain-specific knowledge to
improve its ability to ge... / knowledge to select a neural network's topology and initial br to refine the topology of the neural networks they produce thereby
4992.2 A Brief History of Connectionism - Medler (1998)(Correct)
Connectionist research is firmly established within the scientific community, especially within the
multi-disciplinary field of cognitive science. This diversity, however, has created an environment
w... / concludes by suggesting that neural network research-at least in br and Olson have stated The neural network revolution has happened. We
4811.0 Receptive Field Weighted Regression - Schaal, Atkeson (1997)(Correct)
We introduce a constructive, incremental learning system for regression problems that models
data by means of spatially localized linear models. In contrast to other approaches, the size and
shape of ... / functions such as sigmoidal neural networks and that their theoretical br Loader while many neural network learning algorithms focused on
4756.3 Software Reliability Engineering: An Evolutionary Neural Network.. - Hochman (1997)(Correct)
Author: Robert Hochman
Title: Software Reliability Engineering:
An Evolutionary
Neural Network Approach
Institution: Florida Atlantic University
Thesis Advisor: Dr. Taghi M. Khoshgoftaar
Degree: Maste... / Engineering An Evolutionary Neural Network Approach By Robert Hochman
4580.6 DistAl: An Inter-pattern Distance-based Constructive Learning.. - Yang, Parekh, Honavar (1997)(Correct)
Multi-layer networks of threshold logic units offer an attractive framework for the
design of pattern classification systems. A new constructive neural network learning
algorithm (DistAl) based on int... / systems. A new constructive neural network learning algorithm DistAl br compares favorably with other neural network learning algorithms for
4563.9 Unsupervised Neural Network Learning Procedures For Feature.. - Suzanna Becker, Mark Plumbley (1996)(Correct)
In this article, we review unsupervised neural network learning procedures which can be
applied to the task of preprocessing raw data to extract useful features for subsequent classification.
The lear... / Unsupervised Neural Network Learning Procedures For br Issue on Applications of Neural Networks Vol. No. F. Pineda
4554.8 Robust Automatic Speech Recognition With Unreliable Data - Josifovski (1999)(Correct)
Theoretical and practical issues of some of the problems in robust automatic speech recognition
(ASR) and some of the techniques that address them are presented in this report. The problem
of the robu... / models HMM and artificial neural networks ANN This is referred to as br imputation with artificial neural networks as posterior estimators .
4524.3 Modular Connectionist Architectures and the Learning of.. - Bale (1998)(Correct)
Modular connectionist systems comprise autonomous, communicating modules, achieving a
behaviour more complex than that of a single neural network. The component modules,
possibly of different topologi... / complex than that of a single neural network. The component modules br . Modular Neural
4498.2 An Overview of Corpus-Based Statistics-Oriented (CBSO) Techniques for .. - Su, Chiang, Chang (1996)(Correct)
A Corpus-Based Statistics-Oriented (CBSO) methodology, which is an attempt to avoid the drawbacks
of traditional rule-based approaches and purely statistical approaches, is introduced in this paper. R... / connectionist approaches i.e.neural network approaches Cottrell br of IEEE Workshop Neural Networks for Signal Processing pp.
4315.4 Esprit Bra Iii Project Nat 7130 - Number March(Correct)
Contents
Editor's message 1
Objectives of the research carried out in
NAT 1
Results of the research carried out in NAT 4
Conclusions 13
List of Publications 16
Anonynous ftp sites 28
NAT Consortium 2... / invariant transforms and neural networks. The techniques developed br to merge and cross-fertilize neural network techniques with other
4246.3 Feature Subset Selection Using A Genetic Algorithm - Yang, Honavar (1997)(Correct)
Practical pattern classification and knowledge discovery problems require selection of a subset of attributes or features (from a much larger set) to represent the patterns to be classified. This is... / in the automated design of neural networks for pattern classification br tree induction algorithm or a neural network learning algorithm The
4236.6 Convergence-Zone Episodic Memory: Analysis and Simulations - Moll, Miikkulainen (1997)(Correct)
Human episodic memory provides a seemingly unlimited storage for everyday experiences, and a
retrieval system that allows us to access the experiences with partial activation of their components.
The ... / This paper presents a neural network model of the hippocampal br of this paper appeared in Neural Networks - . y
4211.0 Passively Learning Finite Automata - Murphy (1995)(Correct)
We provide a survey of methods for inferring the structure of a finite automaton from passive observation
of its behavior. We consider both deterministic automata and probabilistic automata (similar t... / . . Neural network methods br comment can be made about neural networks. We are interested
4199.7 Natural Language Grammatical Inference with Recurrent Neural Networks - Lawrence, Giles, Fong (1998)(Correct)
This paper examines the inductive inference of a complex grammar with neural networks -- specifically, the task considered is that of training a network to classify natural language sentences as gramm... / Inference with Recurrent Neural Networks Steve Lawrence C. Lee br of a complex grammar with neural networks -specifically the task
4094.5 Separating Formal Bounds from Practical Performance in Learning.. - Cohn (1992)(Correct)
Separating Formal Bounds from Practical Performance in Learning
Systems
by David Cohn
Chairperson of Supervisory Committee:
Richard Ladner
Department of Computer Science and Engineering
Learning the... / . . Neural networks br Theory versus Practice of Neural Network Generalization .
4083.8 Knowledge-Based Artificial Neural Networks - Geoffrey Towell (1994)(Correct)
Hybrid learning methods use theoretical knowledge of a domain and a set of classified
examples to develop a method for accurately classifying examples not seen during
training. The challenge of hybrid... / Knowledge-Based Artificial Neural Networks Geoffrey G. Towell br Knowledge-Based Artificial Neural Networks Current address is
4034.4 Recurrent Neural Networks for Adaptive Temporal Processing - Bengio, Frasconi, Gori, Soda(Correct)
Compared to other existing approaches to deal with temporal data, recurrent networks
have generated interest mostly because of their capability of implementing adaptive long-term
memories. However, op... / Recurrent Neural Networks for Adaptive Temporal br adaptive systems and artificial neural networks. Introduction The
3974.0 Evolution of Homing Navigation in a Real Mobile Robot - Floreano, Mondada (1996)(Correct)
In this paper we describe the evolution of a discrete-time recurrent neural network to control a real mobile robot. In all our experiments the evolutionary procedure is carried out entirely on the phy... / of a discrete-time recurrent neural network to control a real mobile br Robots Genetic Algorithms Neural Networks. I. Introduction A
3968.9 Input/Output HMMs for Sequence Processing - Bengio, Frasconi (1995)(Correct)
We consider problems of sequence processing and propose a solution based on a discrete state model in order to represent past context. We introduce a recurrent connectionist architecture having a modu... / processing style as recurrent neural networks. IOHMMs are trained using a br prediction. Feedforward neural networks are inadequate in many of
3940.1 Evolutionary Algorithms for Neural Network Design and Training - Branke (1995)(Correct)
Neural networks and genetic algorithms are two relatively young research areas
that were subject to a steadily growing interest during the past years. Both models
are inspired by nature, but whereas n... / Evolutionary Algorithms for Neural Network Design and Training Jurgen br January Abstract Neural networks and genetic algorithms are
3913.6 Some Topics in Neural Networks and Control - Sontag (1993)(Correct)
This report constitutes an expanded version of a presentation given by the author at the
1993 European Control Conference (short course on "Neural Nets for Control"). The first
part places neurocontro... / Some Topics in Neural Networks and Control Eduardo D. br D. Sontag Some Topics in Neural Networks and Control Eduardo D.
3845.8 On the Applicability of Neural Network and Machine Learning.. - Lawrence, Giles, Fong (1995)(Correct)
We examine the inductive inference of a complex grammar - specifically, we consider the task of
training a model to classify natural language sentences as grammatical or ungrammatical, thereby exhibit... / On the Applicability of Neural Network and Machine Learning br following models feed-forward neural networks Fransconi-Gori-Soda and
3809.7 Self-Organizing Maps And Software Reuse - Merkl (1998)(Correct)
Software reuse is the process of building new systems from existing
components instead of developing these systems from scratch. For a long
time now software reuse is repeatedly acknowledged for playi... / map i.e. an unsupervised neural network model to determine the mutual br of selforganizing maps the neural network model we rely on for software
3795.5 Inductive Logic Programming for Natural Language Processing - Raymond Mooney (1997)(Correct)
This paper reviews our recent work on applying inductive
logic programming to the construction of natural language processing
systems. We have developed a system, Chill, that learns a parser from a
... / of recent research on applying neural-network techniques such as simple br that learns to control a neural-network parsing architecture that
3778.3 A Delay Damage Model Selection Algorithm for NARX Neural Networks - Lin, Giles, Horne, Kung(Correct)
Recurrent neural networks have become popular models for system identification and time
series prediction. NARX (Nonlinear AutoRegressive models with eXogenous inputs) neural
network models are a popu... / Selection Algorithm for NARX Neural Networks Tsungnan Lin y br Abstract Recurrent neural networks have become popular models
3754.6 Varieties of Helmholtz Machine - Dayan, Hinton (1996)(Correct)
The Helmholtz machine is a new unsupervised learning architecture that uses topdown
connections to build probability density models of input and and bottom up
connections to build inverses to those mo... / learning algorithms for neural networks usually have the clear and br to clarify this point. For a neural network to be of any value at all
3729.4 A Lagrangian Relaxation Network for Graph Matching - Rangarajan, Mjolsness (1996)(Correct)
A Lagrangian relaxation network for graph matching is presented. The problem is formulated as follows: given graphs G and g, find a permutation matrix M that brings the two sets of vertices into corre... / IEEE Transactions on Neural Networks in press A Lagrangian br matching are usually required. Neural network approaches to graph matching
3696.2 Evolution and Development of Control Architectures in Animats - Kodjabachian, Meyer (1996)(Correct)
This paper successively describes the works of Boers & Kuiper, Gruau, Cangelosi et
al., Vaario, Dellaert & Beer, and Sims, which all evolve the developmental program of an
artificial nervous system. T... / on the evolutionary design of neural networks a particular class of br are encountered when evolving neural networks with such methods problems
3669.6 A Neural Network Based Hybrid System for Detection, Characterization.. - Ghosh, Deuser, Beck (1992)(Correct)
Automated identification and classification of short-duration oceanic signals obtained
from passive sonar is a complex problem because of the large variability in both temporal
and spectral characteri... / A Neural Network Based Hybrid System for br purpose. A variety of static neural network classifiers are evaluated and
3665.5 Fuzzy Finite-state Automata Can Be Deterministically Encoded into.. - Omlin, Thornber, Giles (1998)(Correct)
There has been an increased interest in combining fuzzy systems with neural networks because fuzzy
neural systems merge the advantages of both paradigms. On the one hand, parameters in fuzzy systems
h... / Encoded Into Recurrent Neural Networks Christian W. Omlin a br in combining fuzzy systems with neural networks because fuzzy neural systems
3589.8 On the misuses of artificial neural networks for prognostic and.. - Schwarzer, Vach, Schumacher(Correct)
The application of artificial neural networks (ANNs) for prognostic and diagnostic
classification in clinical medicine has become very popular. Some indications might
be derived from a recent "mini-se... / On the misuses of artificial neural networks for prognostic and br The application of artificial neural networks ANNs for prognostic and
3567.6 Alternative Analysis for Computational Holon Architectures - Zeigler, Vahie, Kim (1994)(Correct)
Simulator : : : : : : : : : : : : : : : : : : : : : : : : : 87
Appendix E. Examples of Human Performance Process Hierarchical Decomposition
92
Appendix F. Scalable Coherent Interfaces 96
Contents (c... / Appendix C. Neural Networks An Overview Appendix D. br C. A Back Propagation Neural Network
3507.4 Networks of Spiking Neurons: The Third Generation of Neural Network.. - Maass (1997)(Correct)
The computational power of formal models for networks of spiking neurons
is compared with that of other neural network models based on McCulloch
Pitts neurons (i.e. threshold gates), respectively sigm... / The Third Generation of Neural Network Models Wolfgang Maass br is compared with that of other neural network models based on McCulloch
3464.1 Unsupervised Classification Learning from Cross-Modal Environmental.. - de Sa (1994)(Correct)
This dissertation addresses the problem of unsupervised learning for pattern classification
or category learning. A model that is based on gross cortical anatomy and
implements biologically plausible ... / and general perspective of the neural network field. Randal Nelson's br Lang for bringing me into the neural network fold and for many interesting
3438.1 Multitask Learning - Caruana (1997)(Correct)
Multitask Learning is an approach to inductive transfer that improves generalization by using the
domain information contained in the training signals of related tasks as an inductive bias. It does ... / the same domain. An artificial neural network or a decision tree or a . br Y. S.Learning from Hints in Neural Networks Journal of Complexity
3413.4 Common Control Principles Of Basal Ganglia - Thalamocortical Loops.. - Lörincz (1996)(Correct)
The learning features of the hippocampal formation and the basal ganglia -- thalamocortical loops are analysed on the basis of their recent models utilizing control concepts for both architectures. ... / Neural Network World in press URL br c flIDG Neural Network World -xx .
3404.6 Cortical Synchronization and Perceptual Framing - Grossberg, Grunewald (1996)(Correct)
How does the brain group together different parts of an object into a coherent visual
object representation? Different parts of an object may be processed by the brain at different
rates and may thus ... / framing visual cortex neural network boundary contour system br to the same retinal object. A neural network model is presented that is
3397.9 Information Geometric Measurements of Generalisation - Zhu, Rohwer (1995)(Correct)
Neural networks can be regarded as statistical models, and can be analysed in a
Bayesian framework. Generalisation is measured by the performance on independent
test data drawn from the same distribut... / August Abstract Neural networks can be regarded as br on the issue of evaluating neural network learning rules and other
3383.5 Combining Exploratory Projection Pursuit And Projection Pursuit.. - Intrator (1992)(Correct)
We present a novel classification and regression method that combines exploratory projection
pursuit (unsupervised training) with projection pursuit regression (supervised training), to yield
a new fa... / Regression With Application To Neural Networks Nathan Intrator yz br and unsupervised artificial neural network ANN is described as a
3359.4 Memory-Based Neural Networks For Robot Learning - Atkeson, Schaal (1995)(Correct)
This paper explores a memory-based approach to robot learning, using memorybased
neural networks to learn models of the task to be performed. Steinbuch and
Taylor presented neural network designs to e... / Memory-Based Neural Networks For Robot Learning br learning using memorybased neural networks to learn models of the task
3349.0 Neural Networks for Signal Processing - Svarer(Correct)
i
Abstract
In this thesis, methods for optimization of neural network architectures are examined in
order to achieve better generalization ability from the neural networks at tasks within
signal pro... / Neural Networks for Signal Processing br methods for optimization of neural network architectures are examined in
3332.1 From Natural to Artificial Life: Biomimetic Mechanisms in Animat.. - Meyer (1997)(Correct)
This paper describes several models that incorporate some biomimetic mechanisms into
the control architecture of an animat that has to survive in a changing environment. The
adaptive capacities of the... / input to an analog parallel neural network designed to implement an br system. The upper module of the neural network bordered in gray is the
3307.2 A Framework for Combining Symbolic and Neural Learning - Shavlik (1992)(Correct)
This article describes an approach to combining symbolic and connectionist approaches to
machine learning. A three-stage framework is presented and the research of several groups is
reviewed with resp... / of symbolic knowledge into neural networks the second addresses the br Keywords knowledge-based neural networks theory refinement use of
3301.3 Learning, Representation, and Synthesis of Discrete Dynamical Systems .. - Giles, Omlin (1995)(Correct)
This paper gives an overview on
learning and representation of discrete-time,
discrete-space dynamical systems in discretetime,
continuous-space recurrent neural networks.
We limit our discussion to d... / Systems in Continuous Recurrent Neural Networks C. Lee Giles ab br continuous-space recurrent neural networks. We limit our discussion to
3301.1 How to Build VLSI-Efficient Neural Chips - Beiu (1998)(Correct)
This paper presents several upper and lower
bounds for the number-of-bits required for solving a classification
problem, as well as ways in which these bounds can
be used to efficiently build neural n... / be used to efficiently build neural network chips. The focus will be on br aspects pertaining to neural networks i size complexity and
3293.8 Neuro-Fuzzy Systems In Control - Ojala (1994)(Correct)
Tiivistelmä
List of abbreviations
List of symbols
1 Introduction
2 Basics of neural networks
2.1 Biological and artificial neural networks . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
... / Introduction Basics of neural networks . Biological and br . Biological and artificial neural networks .
3282.2 Living in a partially structured environment: How to bypass the.. - Gaussier, Revel, Joulain, Zrehen (1996)(Correct)
In this paper, we propose an unsupervised neural network allowing a robot to learn sensori-motor
associations with a delayed reward. The robot task is to learn the "meaning" of pictograms in order
to ... / we propose an unsupervised neural network allowing a robot to learn br based on image recognition. Neural Networks Unsupervised Learning
3275.1 Map Learning and High-Speed Navigation in RHINO - Thrun, Bücken, Burgard, Fox.. (1998)(Correct)
This chapter surveys basic methods for learning maps and high speed autonomous navigation for indoor
mobile robots. The methods have been developed in our lab over the past few years, and most of them... / algorithms such as artificial neural networks interpret the robot's br and the cameras. Artificial neural networks are used to interpret sonar
3265.5 A New Evolutionary System for Evolving Artificial Neural Networks - Yao (1996)(Correct)
This paper presents a new evolutionary system, i.e., EPNet, for evolving artificial neural networks (ANNs). The evolutionary algorithm used in EPNet is based on Fogel's evolutionary programming (EP) [... / Ieee Transactions On Neural Networks A New Evolutionary System br System for Evolving Artificial Neural Networks Xin Yao S.M.IEEE and
3256.5 Digital Neural Network Implementations - Burr (1995)(Correct)
This chapter gives an overview of existing digital VLSI implementations and discusses techniques for implementing high performance, high capacity digital neural nets. It presents a set of techniques f... / Digital Neural Network Implementations James B. br networks. Introduction Neural network applications suitable for
3249.1 Successes And Failures Of Backpropagation: A Theoretical Investigation - Frasconi, Gori, Tesi(Correct)
Introduction
Backpropagation is probably the most widely applied neural network learning algorithm.
Backprop's popularity is related to its ability to deal with complex multi-dimensional
mappings. In... / the most widely applied neural network learning algorithm. br That idea never occurred to neural network researchers throughout the
3235.5 Continuous-based Heuristics for Graph and Tree Isomorphisms, with.. - Pelillo, Siddiqi, Zucker (1999)(Correct)
We present a new (continuous) quadratic programming approach for graph- and
tree-isomorphism problems which is based on an equivalent maximum clique
formulation. The approach is centered around a fund... / Durbin and Willshaw the neural network community also became br state-of-the-art sophisticated neural network algorithms which by contrast
3212.8 A Global Optimization Technique for Statistical Classifier Design - Miller, Rao, Rose, Gersho(Correct)
A global optimization method is introduced for the design of statistical classifiers that minimize
the rate of misclassification. We first derive the theoretical basis for the method, based on which
w... / to the increasing interest in neural network models and in their br applications. MLPs and other neural network models have been investigated
3208.3 Constructive Neural Network Learning Algorithms for Pattern.. - Parekh, Yang, Honavar (1998)(Correct)
Constructive learning algorithms offer an attractive approach for the incremental construction of near-minimal neural network architectures for pattern classification. They help overcome the need for ... / Constructive Neural Network Learning Algorithms for br construction of near-minimal neural network architectures for pattern
3162.4 Relational Learning Techniques for Natural Language Information.. - Califf (1998)(Correct)
The recent growth of online information available in the form of natural language documents creates a greater need for computing systems with the ability to process those documents to simplify access ... / significant research applying neural-network methods to language processing
3154.8 Efficient Approximations for the Marginal Likelihood of Bayesian.. - Chickering, Heckerman (1996)(Correct)
We discuss Bayesian methods for model averaging and model selection among Bayesiannetwork
models with hidden variables. In particular, we examine large-sample approximations
for the marginal likelihoo... / learning for probabilistic neural-network models. In this paper we br respectively in feed-forward neural networks. Roughly speaking in using
3149.4 The Role of Afferent Excitatory and Lateral Inhibitory Synaptic.. - Kalarickal, Marshall (1998)(Correct)
Previous models of visual cortical ocular dominance (OD) plasticity
(e.g., Clothiaux et al., 1991; Miller et al., 1989) are based on afferent excitatory
synaptic plasticity alone; these models do not ... / plasticity self-organization neural networks EXIN excitatory br We have formulated and tested a neural network model that exhibits OD changes
3092.1 On the Analysis of Pattern Sequences by Self-Organizing Maps - Kangas (1994)(Correct)
This thesis is organized in three parts. In the first part, the Self-Organizing Map algorithm is introduced. The discussion focuses on the analysis of the Self-Organizing Map algorithm. It is shown th... / Map iv . Neural Networks and Analysis of Pattern br . . Time-Delay Neural Network
3091.9 Hierarchical Bayesian-Kalman Models For Regularisation And ARD In.. - de Freitas, Niranjan, Gee (1998)(Correct)
In this paper, we show that a hierarchical Bayesian modelling approach to sequential
learning leads to many interesting attributes such as regularisation and automatic
relevance determination. We iden... / Sequential training of neural networks is important in applications br Sutton's ideas to nonlinear neural networks and relate them to other
3082.6 Synthesizing Regularity Exposing Attributes in Large Protein Databases - Maza (1993)(Correct)
This thesis describes a system that synthesizes regularity exposing attributes from
large protein databases. After processing primary and secondary structure data, this
system discovers an amino acid ... / structure prediction. A neural network trained using this bit br to the one achieved by a neural network trained using the standard
3062.2 Neural Networks and Statistical Models - Sarle (1994)(Correct)
There has been much publicity about the ability of artificial neural
networks to learn and generalize. In fact, the most commonly
used artificial neural networks, called multilayer perceptrons, are
no... / Neural Networks and Statistical Models br the ability of artificial neural networks to learn and generalize. In
3034.9 Empirical Risk Approximation: An Induction Principle for Unsupervised .. - Buhmann (1998)(Correct)
Unsupervised learning algorithms are designed to extract structure from data without
reference to explicit teacher information. The quality of the infered structure is determined
by a quality function... / al. and various other neural network models Poggio and Girosi br Cambridge UK under the Neural Networks and Machine Learning
2975.2 Gated Modular Neural Networks for Control Oriented Modelling - Roncoy Peter(Correct)
This study is an attempt to review the main "Gated Modular Neural Networks" (GMNNs)
which are particularly suitable for modelling oriented toward control. A GMNN consists
of a network of computing mod... / Gated Modular Neural Networks for Control Oriented br review the main Gated Modular Neural Networks GMNNs which are
2972.3 Brain-size Neurocomputers: Analyses and simulations of neural.. - Heemskerk, Murre (1995)(Correct)
Current neurocomputers are more than 50 million times slower than the brain. Although chip speeds exceed
the switching speed of biological neurons with several orders of magnitude, artificial neural n... / orders of magnitude artificial neural networks are of a much smaller scale br than implementing large-scale neural networks. In order to simulate neural
2967.7 Neurocontrol III: Differencing Models Of Basal.. - Lörincz (1997)(Correct)
Two models of basal ganglia--thalamocortical loops are proposed, both of which feature population coding and utilize local approximations. The first model is a temporal differencing scheme similar t... / Neural Network World - URL br are discussed. Key words Neural network neurocontrol dynamic
2967.6 Time in Connectionist Models - Chappelier, Gori, Grumbach(Correct)
Introduction
There exist two different kinds of knowledge representation in Artificial Intelligence:
explicit, that can be represented by symbolic expressions, and implicit (i.e.
non-symbolic), whic... / of temporal processing with neural networks. Several temporal br of the chapter focuses only on neural network architectures that handle an
2945.2 Phoneme Probability Estimation with Dynamic Sparsely Connected.. - Ström (1997)(Correct)
This paper presents new methods for training large neural networks for phoneme
probability estimation. An architecture combining time-delay windows and
recurrent connections is used to capture the imp... / Sparsely Connected Artificial Neural Networks Nikko Strm br new methods for training large neural networks for phoneme probability
2943.2 Classification Of Spatio-Temporal Patterns With Applications To.. - Ghosh, Deuser (1995)(Correct)
this article, the wavelet transform is used
to generate sixteen coefficients that describe the spectral characteristics of the signal.
These sixteen coefficients are augmented with temporal descriptor... / reviews possible artificial neural network mechanisms for the br form. Since most artificial neural network approaches to classifying
2931.0 What Size Neural Network Gives Optimal Generalization? Convergence.. - Lawrence, Giles, Tsoi (1996)(Correct)
One of the most important aspects of any machine learning paradigm is how it scales according
to problem size and complexity. Using a task with known optimal training error, and a pre-specified
maximu... / What Size Neural Network Gives Optimal Generalization br following occur often in the neural network literature and community .
2907.5 Visual Schemas in Neural Networks for Object Recognition and Scene.. - Leow, Miikkulainen (1997)(Correct)
VISOR is a large connectionist system that shows how visual schemas can be learned, represented,
and used through mechanisms natural to neural networks. Processing in VISOR is based
on cooperation, co... / Visual Schemas in Neural Networks for Object Recognition and br through mechanisms natural to neural networks. Processing in VISOR is based
2906.7 Noisy Time Series Prediction using Symbolic Representation and.. - Lawrence (1997)(Correct)
Financial forecasting is an example of a signal processing problem which is challenging due
to small sample sizes, high noise, non-stationarity, and non-linearity. Neural networks have been
very succe... / Representation and Recurrent Neural Network Grammatical Inference Steve br and non-linearity. Neural networks have been very successful in
2882.4 Studying the Role of Embodiment in Cognition - Mataric (1997)(Correct)
This paper raises the question of the connection
between embodiment and higher-level cognition
which has been eloquently addressed before, but
has not yet received much focus in the AI community.
The ... / embraced variations of neural-network models that present a
2859.1 Automatic Text Detection and Tracking in Digital Video - Li, Doermann, Kia (1998)(Correct)
Text which either appears in a scene or is graphically added to video can provide an important
supplemental source of index information as well as clues for decoding the video's structure
and for clas... / Indexing Digital Libraries Neural Network Wavelet The support of br We use a hybrid wavelet neural network segmenter Figure to
2825.1 An Investigation of Hybrid Systems for Reasoning in Noisy Domains - Melvin (1995)(Correct)
This thesis discusses aspects of design, implementation and theory of expert systems,
which have been constructed in a novel way using techniques derived from
several existing areas of Artificial Inte... / described as Artificial Neural Network approaches into one br Functional Characteristics of Neural Networks . Fuzzy
2805.8 Dynamic Recurrent Neural Networks - Pearlmutter (1990)(Correct)
We survey learning algorithms for recurrent neural networks with hidden units and attempt
to put the various techniques into a common framework. We discuss fixpoint learning algorithms,
namely recurre... / Dynamic Recurrent Neural Networks Barak A. Pearlmutter br algorithms for recurrent neural networks with hidden units and attempt
2804.3 Statistical Analysis of Learning Dynamics - Murata, Amari(Correct)
Learning is a flexible and effective means of extracting the stochastic structure
of the environment. It provides an effective method for blind separation and deconvolution
in signal processing. Two d... / of the environment and neural networks are utilized for solving br statistical understanding of neural network-based adaptive signal
2776.4 Neural Dynamics Of Variable-Rate Speech Categorization - Grossberg, Boardman, Cohen (1995)(Correct)
What is the neural representation of a speech code as it evolves in real time? A neural
model of this process, called the ARTPHONE model, is developed to quantitatively simulate
data concerning segreg... / memory chunking attention neural network adaptive resonance theory br leads to the development of a neural network model of the interactive
2769.6 Making the World Differentiable: On Using Self-Supervised Fully.. - Jürgen Schmidhuber (1990)(Correct)
First a brief introduction to reinforcement learning and to supervised learning with recurrent
networks in non-stationary environments is given. The introduction also covers the basic principle of
`g... / Fully Recurrent Neural Networks for Dynamic Reinforcement br for a reinforcement learning neural network with internal and external
2760.9 Neural Modeling of Psychiatric Disorders - Ruppin (1995)(Correct)
This paper reviews recent neural modeling studies of psychiatric disorders.
Numerous aspects of psychiatric disturbances have been investigated,
such as the role of synaptic changes in the pathogenesi... / psychological communities in neural network modeling see e.g.Cohen br the microscopic' features of neural networks of the brain such as the
2758.2 UNH_CMAC Version 2.1 - The University of New Hampshire Implementation .. - Miller, Glanz (1996)(Correct)
this document as "layers" (the layers represent parallel N-dimensional
hyperspaces for a network with N inputs). The receptive fields in each of the layers have
rectangular boundaries and are organize... / principles of the CMAC neural network as proposed by Albus - br The response of the CMAC neural network to a given input is the
2757.6 A Neural Network Architecture for Syntax Analysis - Chen, Honavar(Correct)
Artificial neural networks (ANNs), due to their inherent parallelism
and potential fault tolerance, offer an attractive paradigm for
robust and efficient implementations of syntax analyzers. This pape... / A Neural Network Architecture for Syntax br CS-TR - August A Neural Network Architecture for Syntax
2749.5 Multimedia Information Access - de Vries (1995)(Correct)
The problem of information overload can be solved by the
application of information retrieval systems to the huge
amount of data. This application in mind, the design of
a multimedia information acces... / . . . Development of a neural network . br . . . Evaluation of the neural network segmenter .
2724.9 Foundations of Knowledge Representation and Reasoning - Lakemeyer, Nebel (1994)(Correct)
this paper is not by itself a paper on computational
complexity analysis of commonsense reasoning, it makes use of computational
complexity results [ Gottlob, 1992 ] that show that the three main form... / as patterns of activation in a neural network research in the area of br e.g.programming languages and neural networks. Explicitness of
2723.7 Pattern classification - Denoeux (1996)(Correct)
Pattern classification consists in assigning entities, described by feature
vectors, to predefined groups of patterns. When the statistical characteristics
of the problem under consideration are perfe... / from training data. Several neural network approaches to this problem br a taxonomy of the main neural network and alternative techniques to
2714.4 A Measurement-based Admission Control Algorithm for Integrated.. - Jamin, Danzig, Shenker, Zhang (1995)(Correct)
Many designs for integrated services networks offer a
bounded delay packet delivery service to support real-time applications.
To provide bounded delay service, networks must use admission
control t... / references Hir CLG a neural network is used for dynamic bandwidth br Capacity Control by Distributed Neural Network IEEE Journal of Selected
2713.1 Challenges in Evolving Controllers for Physical Robots - Mataric, Cliff (1996)(Correct)
This paper discusses the feasibility of applying evolutionary methods
to automatically generating controllers for physical mobile robots.
We overview the state of the art in the field, describe some o... / continuous-time recurrent neural network controllers for artificial br evolving parameters for a neural network governing leg movements in a
2709.6 A Bayesian Approach to Landmark Discovery and Active Perception in.. - Thrun (1996)(Correct)
To operate successfully in indoor environments, mobile robots must be able to localize themselves.
Over the past few years, localization based on landmarks has become increasingly popular. Virtually a... / This is done by training neural network landmark detectors so as to br active vision artificial neural networks Bayesian analysis
2707.3 Feature Weighting for Lazy Learning Algorithms - Aha (1998)(Correct)
Learning algorithms differ in the degree to which they process their inputs
prior to their use in performance tasks. Many algorithms eagerly compile input
samples and use only the compilations to m... / a rule set decision tree or neural network and use it to process br Expert Systems and Neural Networks pages - . Unpublished.
2686.9 Evolution and Development of Neural Networks Controlling Locomotion.. - Jerome Kodjabachian (1997)(Correct)
This paper describes how the SGOCE paradigm has been
used to evolve developmental programs capable of generating neural networks
that control the behavior of simulated insects. This paradigm is charac... / Evolution and Development of Neural Networks Controlling Locomotion br programs capable of generating neural networks that control the behavior of
2680.9 Face Recognition: A Convolutional Neural Network Approach - Lawrence, Giles, Tsoi, Back (1997)(Correct)
Faces represent complex, multidimensional, meaningful visual stimuli and developing a computational model for face recognition is difficult [43]. We present a hybrid neural network solution which comp... / IEEE Transactions on Neural Networks Special Issue on Neural br Networks Special Issue on Neural Networks and Pattern Recognition
2679.3 Ago Ergo Sum - Floreano (1997)(Correct)
In this paper I explore the hypothesis that some of today robots might
possess a form of consciousness whose substrate is a mere algorithm. First,
consciousness is defined within an evolutionary frame... / e.g.an artificial neural network a rule-based system a br of algorithm an artificial neural network which maps input vectors into
2669.6 The sample complexity of pattern classification with neural networks: .. - Bartlett (1997)(Correct)
Sample complexity results from computational learning theory, when applied to
neural network learning for pattern classification problems, suggest that for good generalization
performance the number o... / of pattern classification with neural networks the size of the weights is br theory when applied to neural network learning for pattern
2661.8 SemQuery: Semantic Clustering and Querying on Heterogeneous Features.. - Sheikholeslami, Chang, Zhang (1998)(Correct)
The effectiveness of the content-based image retrieval can be enhanced using the heterogeneous
features embedded in the images. However, since the features in texture, color, and shape
are generated u... / We also design a multi-layer neural network model to merge the results of br features. The input to the neural network is the set of image features
2628.6 Neural Networks - Baddeley(Correct)
Introduction
This chapter is aimed at the physiologist new to neural networks and the student
wishing to experiment for the first time. The chapter will describe general
principles the author has fou... / Chapter Neural Networks Roland Baddeley . br at the physiologist new to neural networks and the student wishing to
2624.0 Nonlinear Partial Least Squares - Malthouse (1995)(Correct)
Nonlinear Partial Least Squares Edward Carl Malthouse We propose a new nonparametric regression method for high-dimensional data, nonlinear partial least squares (NLPLS). NLPLS is motivated by project... / pursuit PPR and feedforward neural networks. The model takes the form of br NLPLS with feedforward neural networks. NLPLS will often produce a
2612.1 A Study of the Use and Evaluation of Confidence Measures in Automatic .. - Williams (1998)(Correct)
Confidence measures have been found to be useful for a number tasks within the field of Automatic
Speech Recognition (ASR). For example, the use of confidence measures has been reported in the utteran... / Hidden Markov Model Artificial Neural Network HMM ANN systems are well br Hidden Markov Model Artificial Neural Network HMM ANN based
2600.8 Equivalence in Knowledge Representation: Automata, Recurrent Neural.. - Omlin, Giles, Thornber (1998)(Correct)
Neuro-fuzzy systems - the combination of artificial neural networks with fuzzy logic - are becoming
increasingly popular. However, neuro-fuzzy systems need to be extended for applications which requir... / Automata Recurrent Neural Networks and Dynamical Fuzzy Systems br -the combination of artificial neural networks with fuzzy logic -are
2597.4 Finite Impulse Response Neural Networks for Autoregressive Time.. - Wan (1993)(Correct)
A neural network architecture, which models synapses as Finite Impulse Response
(FIR) linear filters, is discussed for use in time series prediction. Analysis and
methodology are detailed in the conte... / . Finite Impulse Response Neural Networks for Autoregressive Time br Abstract A neural network architecture which models
2585.8 Learning Maps for Indoor Mobile Robot Navigation - Thrun, Bücken (1998)(Correct)
Autonomous robots must be able to learn and maintain models of their environments.
Research on mobile robot navigation has produced two major paradigms
for mapping indoor environments: grid-based and ... / exploration mobile robots neural networks occupancy grids path br are learned using artificial neural networks and Bayesian integration.
2573.0 Population Based Incremental Learning: A Method for Integrating.. - Baluja (1994)(Correct)
Genetic algorithms (GAs) are biologically motivated adaptive systems which have been used,
with varying degrees of success, for function optimization. In this study, an abstraction of the
basic geneti... / algorithms and artificial neural networks are two recently developed br effort in the field of neural networks and competitive learning has
2562.4 A Constructive Connectionist Approach Towards Continual Robot Learning - Großmann, Poli (1997)(Correct)
This work presents an approach for combining reinforcement learning, learning by imitation, and incremental
hierarchical development. The approach is used in a realistic simulated mobile robot that le... / in a constructive high-order neural network. Preliminary experiments are br by imitation constructive neural networks. Introduction The goal
2561.0 Generalization - Wah (1998)(Correct)
In this paper, we define the generalization problem, summarize various approaches in
generalization, identify the credit assignment problem, and present the problem and some
solutions in measuring gen... / systems and artificial neural networks ANNs In contrast to br truck backer and neural-network design The
2560.0 A Geographic Knowledge Representation System for Multimedia.. - Chen, Smith, Larsgaard, Hill, Ramsey(Correct)
Digital libraries serving multimedia information that may be accessed in terms of geographic
content and relationships are creating special challenges and opportunities for networked information
syste... / of the semantic network and neural network representations developed in br Based on semantic network and neural network representations GKRS loosely
2558.8 Continuous speech recognition in the WAXHOLM dialogue system - Ström (1996)(Correct)
This paper presents the status of the continuous speech recognition engine of the
WAXHOLM project. The engine is a software only system written in portable C
code. The design is flexible and different... / In particular artificial neural networks and standard multiple br An artificial neural network ANN mode implementing a
2557.7 Minimizing Conflicts: A Heuristic Repair Method for.. - Minton, Johnston, Philips, Laird (1992)(Correct)
This paper describes a simple heuristic approach to solving large-scale constraint satisfaction and
scheduling problems. In this approach one starts with an inconsistent assignment for a set of variab... / by a surprisingly effective neural network developed by Adorf and br review of Adorf and Johnston's neural network and then describe our
2555.2 Networks For Speech Enhancement - Wan, Nelson (1998)(Correct)
Introduction
1.1. Background
Speech enhancement is motivated by the need to improve the performance of
voice communications systems in noisy conditions. Applications range from frontends
for speech ... / Handbook of Neural Networks for Speech Processing First br recent years several distinct neural network based frameworks have emerged
2548.1 Activity-Dependent Outgrowth of Neurons and Overshoot Phenomena in.. - van Ooyen, van Pelt (1994)(Correct)
During the development of the nervous system, all kinds of structural elements
such as neurons, neuritic extensions and synapses are initially overproduced (socalled
overshoot phenomena). Neurite outg... / Phenomena in Developing Neural Networks Arjen van Ooyen Jaap van br assembled into functional neural networks during development. Among
2531.2 From continuous dynamics to symbols - Jaeger (1997)(Correct)
This article deals with mathematical models of discrete, identifiable, "symbolic"
events in neural and cognitive dynamics. These dynamical symbols are the supposed
correlates of identifiable motor act... / neuroscience and artificial neural network research. It now becomes br interpretation of recurrent neural networks e.g. or the theory of
2522.4 Exploiting Population Information in Evolutionary Learning - Yao, Liu, Darwen(Correct)
Evolutionary learning has been developing rapidly in the last decade. It is a powerful and general learning approach which has been used successfully in both symbolic systems, e.g., rule-based systems... / systems e.g.artificial neural networks. However most evolutionary br domain of artificial neural networks. The second example is in
2509.8 Factorial Hidden Markov Models - Zoubin Ghahramani, Michael I. Jordan (1997)(Correct)
Hidden Markov models (HMMs) have proven to be one of the most widely used tools
for learning probabilistic models of time series data. In an HMM, information about the past
is conveyed through a sin... / mixture of Gaussians or even a neural network. In the present paper br X t as K separate neural networks one for each setting of S
2504.2 A Tutorial on Support Vector Machines for Pattern Recognition - Burges (1998)(Correct)
The tutorial starts with an overview of the concepts of VC dimension and structural risk minimization. We then describe linear Support Vector Machines (SVMs) for separable and non-separable data, wo... / leave the best performing neural networks severely handicapped and br machine.Thus for example a neural network with fixed architecture with
2499.9 An EM Approach to Learning Sequential Behavior - Bengio, Frasconi (1994)(Correct)
We consider problems of sequence processing and we propose a solution based on a discrete
state model. We introduce a recurrent architecture having a modular structure that
allocates subnetworks to di... / reported in training recurrent neural networks to perform tasks in which br system such as a recurrent neural network will be increasingly
2497.0 Sparse coding with an overcomplete basis set: A strategy employed by.. - Olshausen, Field (1998)(Correct)
The spatial receptive fields of simple cells in mammalian striate cortex have
been reasonably well described physiologically and can be characterized as being
localized, oriented, and bandpass, compa... / by a strictly feedforward neural network in which case the functions br as shown in Figure b. A neural network implementation of this
2489.5 Modular Neural Networks for Learning Context-Dependent Game Strategies - Boyan (1992)(Correct)
The method of temporal differences (TD) is a learning technique which specialises in predicting
the likely outcome of a sequence over time. Examples of such sequences include speech frame
vectors, who... / Modular Neural Networks for Learning br of backgammon indicate that a neural network trained by TD methods to
2486.8 Probabilistic Knowledge Base Validation - Gleason (1995)(Correct)
viii
I. Introduction : : : : : : : : : : : : : : : : : : : : : : : : : : : : : : : : : : : : : : : 1-1
II. V&V... / - . Neural Networks V V br from rule-based and artificial neural network validation strategies. The
2480.6 SHOSLIF-N: SHOSLIF for Autonomous Navigation (Phase II) - Weng, Chen (1995)(Correct)
This report presents an unconventional approach to vision-guided autonomous navigation. The system recalls information about scenes and navigational experience using content-based retrieval from a vis... / robot that couples low-level neural network based modules with high-level br The result was then fed into neural networks to produce a qualitative
2455.7 Pattern Recognition via Neural Networks - Ripley(Correct)
s one of these classes.
Such tasks are called classification or supervised pattern recognition
1
. Clearly
1
The conference proceedings [14] provides a good view of pattern recognition applications... / Pattern Recognition via Neural Networks B. D. Ripley Pattern br many of the applications of neural networks are to classification and
2451.3 An information-maximization approach to blind separation and blind.. - Bell, Sejnowski (1995)(Correct)
We derive a new self-organising learning algorithm which maximises
the information transferred in a network of non-linear units. The algorithm
does not assume any knowledge of the input distributions,... / learning rules for neural networks has been pioneered by Linsker br objective functions applied to neural networks with non-linear units. The
2430.1 Feature-Based Human Face Detection - Kin Choong (1996)(Correct)
Human face detection has always been an important problem for face,
expression and gesture recognition. Though numerous attempts have been
made to detect and localize faces, these approaches have made... / to multiple viewpoints. The neural network approach detects faces by br and then passing it through a neural network filter. Recent work was
2426.0 Bayesian deviance, the effective number of parameters, and the.. - Spiegelhalter, Best, Carlin (1998)(Correct)
We consider the problem of comparing complex hierarchical models in which the number of
parameters is not clearly defined. We follow Dempster in examining the posterior distribution
of the log-likelih... / particular reference to the neural network literature. The contributions br this problem appear in the neural network literature Moody
2406.2 Injecting Nondeterministic Finite State Automata into Recurrent.. - Frasconi, Gori, Soda (1993)(Correct)
In this paper we propose a method for injecting time-warping nondeterministic finite
state automata into recurrent neural networks. The proposed algorithm takes as input
a set of automata transition r... / State Automata into Recurrent Neural Networks Paolo Frasconi Marco Gori br state automata into recurrent neural networks. The proposed algorithm takes
2402.9 Designing Parallel Computers for Self Organizing Maps - Nordström (1992)(Correct)
Self organizing maps (SOM) are a class of artificial neural
network (ANN) models developed by Kohonen. There are a
number of variants, where the self organizing feature map
(SOFM) is one of the most u... / SOM are a class of artificial neural network ANN models developed by br are for simulating artificial neural networks. As an example of bit-serial
2390.2 Redundancy Reduction and Independent Component Analysis: Conditions.. - Nadal (1997)(Correct)
In the context of both sensory coding and signal processing, building factorized codes has been shown to be an efficient strategy. In a wide variety of situations, the signal to be processed is a line... / by using a simple feedforward neural network. In this paper we discuss br processing with a linear neural network model Atick A
2381.9 Visualization and Analysis of 3D Functional Brain Images - Nielsen (1996)(Correct)
The long title of the thesis is: 3D-visualization and neural network analysis of single
subject fMRI 3D functional brain images.
A single subject functional magnetic resonance imaging (fMRI) study is ... / thesis is D-visualization and neural network analysis of single subject br analysis and a feed forward neural network analysis using the entropic
2374.3 On the Computational Power of Discrete Hopfield Nets - Orponen (1993)(Correct)
We prove that polynomial size discrete synchronous Hopfield
networks with hidden units compute exactly the class of Boolean
functions PSPACE/poly, i.e., the same functions as are computed by
polynom... / Recurrent or cyclic neural networks are an intriguing model of br we define a discrete neural network as a -tuple N V I O
2371.4 Soft Classification, a.k.a. Risk Estimation, via Penalized Log.. - Wahba, al. (1993)(Correct)
We discuss a class of methods for the problem of `soft' classification in supervised learning.
In `hard' classification, it is assumed that any two examples with the same attribute vector
will always ... / the other labeled 'If a neural network NN is used for this task br and R. Doursat Neural networks and the bias variance
2370.5 Mapping Neural Networks onto Message-Passing Multicomputers - Ghosh (1989)(Correct)
This paper investigates the architectural requirements for simulating neural
networks using massively parallel multiprocessors. First, we model the connectivity
patterns in large neural networks. A di... / Mapping Neural Networks onto Message-Passing br requirements for simulating neural networks using massively parallel
2343.5 Answering the Connectionist Challenge: A Symbolic Model Of Learning.. - Ling, Marinov (1993)(Correct)
Supporters of eliminative connectionism have argued for a pattern association based
explanation of language learning and language processing. They deny that explicit rules
and symbolic representations... / large extent on two artificial neural network ANN models that are claimed br essential if artificial neural network ANN based cognitive
2341.2 Dual-Mode Dynamics Neural Networks For Combinatorial Optimization - Park (1994)(Correct)
viii
1 Introduction 1
1.1 Combinatorial Optimization Problem and Neural Network : : : : 1
1.2 Related Works : : : : : : : : : : : : : : : : : : : : : : : : : : : : : 3
1.3 Approach of the Thesis : : ... / Dual-Mode Dynamics Neural Networks For Combinatorial br Optimization Problem and Neural Network . Related Works
2329.7 Alternative Discrete-Time Operators and Their Application to.. - Back, al.(Correct)
The shift operator, defined as q x(t) = x(t+1), is the basis for almost all discrete-time
models. It has been shown however, that linear models based on the shift operator
suffer problems when used to... / These problems also arise in neural network models which comprise of br adaptive control and neural networks. These include the delta
2328.6 Non-Parametric Texture Learning - Greenspan (1996)(Correct)
Texture is one of the most informative visual cues that help us understand
our environment. Texture analysis is an important step in many
visual tasks, such as scene segmentation, object recognition, ... / neighbor and feedforward neural-network classifiers. An important br via an optimization process. Neural-network architectures have been
2325.5 Training Mixture Density HMMs with SOM and LVQ - Kurimo (1997)(Correct)
The objective of this paper is to present experiments and discussions of how some neural network algorithms can help the phoneme recognition with mixture density hidden Markov models (MDHMMs). In MD... / University of Technology Neural Networks Research Centre br and discussions of how some neural network algorithms can help the
2317.4 Prediction Risk and Architecture Selection for Neural Networks - Moody (1994)(Correct)
We describe two important sets of tools for neural network modeling:
prediction risk estimation and network architecture selection. Prediction risk is defined
as the expected performance of an estim... / in From Statistics to Neural Networks Theory and Pattern br and Architecture Selection for Neural Networks John Moody Oregon
2310.2 Genetic Set Recombination and its Application to Neural Network.. - Radcliffe (1993)(Correct)
Forma analysis is applied to the task of optimising the connectivity of a feed-forward neural network with a single layer of hidden units. This problem is reformulated as a multiset optimisation probl... / and its Application to Neural Network Topology Optimisation br connectivity of a feed-forward neural network with a single layer of hidden
2305.2 Constructing Computationally Efficient Bayesian Models via.. - Myllymäki, Tirri (1995)(Correct)
Given a set of samples of an unknown probability distribution, we study the problem of
constructing a good approximative Bayesian network model of the probability distribution in
question. This task c... / to a multi-layer feedforward neural network structure The model br increasingly popular in the neural network community since the models
2296.2 Fast Learning VIEWNET Architectures for Recognizing 3-D Objects from.. - Bradski, Grossberg (1995)(Correct)
The recognition of 3-D objects from sequences of their 2-D views is modeled by a family of self-organizing neural architectures, called VIEWNET, that use View Information Encoded With NETworks. VIEWNE... / To appear in the Neural Networks special issue on Automatic br Words Pattern recognition neural networks ART ARTMAP -D object
2294.8 Global Optimisation by Evolutionary Algorithms - Yao (1997)(Correct)
Evolutionary algorithms (EAs) are a class of stochastic
search algorithms applicable to a wide range of problems
in learning and optimisation. They have been
applied to numerous problems in combinator... / optimisation artificial neural network learning fuzzy logic system br Y. Liu Evolving artificial neural networks through evolutionary
2285.3 Recurrent Neural Networks and Prior Knowledge for Sequence.. - Paolo Frasconi (1995)(Correct)
this paper we focus on methods for injecting prior knowledge into adaptive recurrent
networks for sequence processing. In order to increase the flexibility needed for specifying
partially known rules,... / Recurrent Neural Networks and Prior Knowledge for br data. Keywords Recurrent neural networks prior knowledge rule
2283.4 Computational Genetics, Physiology, Metabolism, Neural Systems.. - Yeager(Correct)
This paper discusses a computer model of living organisms and the ecology they exist in called
PolyWorld. PolyWorld attempts to bring together all the principle components of real living systems
into ... / Hebbian learning in arbitrary neural network architectures a visual br embodied in their neural network brains Complex behaviors
2281.5 Making Use of Population Information in Evolutionary Artificial.. - Yao, Liu (1998)(Correct)
This paper is concerned with the simultaneous evolution
of artificial neural network (ANN) architectures and
weights. The current practice in evolving ANNs is to choose
the best ANN in the last genera... / in Evolutionary Artificial Neural Networks Xin Yao SMIEEE and Yong br evolution of artificial neural network ANN architectures and
2275.5 Separation of Speech from Interfering Sounds Based on Oscillatory.. - Wang, Brown (1999)(Correct)
A multi-stage neural model is proposed for an auditory scene analysis task --
segregating speech from interfering sound sources. The core of the model is a twolayer
oscillator network that performs st... / of investigators to propose neural network models of ASA. Perhaps the br the first of these was the neural network model described by von der
2264.0 Adapting Simulated Behaviors For New Characters - Hodgins, Pollard (1997)(Correct)
This paper describes an algorithm for automatically adapting existing
simulated behaviors to new characters. Animating a new character
is difficult because a control system tuned for one character
wil... / Panne and Fiume to produce neural network-based control systems for a
2260.6 A Segmental Approach To Automatic Language Identification - Yeshwant Kumar(Correct)
xx
1 Introduction 1
1.1 The Problem : : : : : : : : : : : : : : : : : : : : : : : : : : : : : : : : : : 1
1.2 Motivation : : : : : : : : : : : : : : : : : : : : : : : : : : : : : : : : : : : 2
1.3 A ... / to my informal knowledge of neural networks and clarified my doubts on br the author of opt the neural network simulation package that I used
2252.1 Understanding Neural Networks as Statistical Tools - Brad Warner (1996)(Correct)
Neural networks have received a great deal of attention over the last few years. They are being used in the
areas of prediction and classification; areas where regression models and other related stat... / Understanding Neural Networks as Statistical Tools br of Mines address. Abstract Neural networks have received a great deal of
2248.1 Complexity Drift in Evolutionary Computation with Tree Representations - Rosca, Ballard (1996)(Correct)
One serious problem of standard Genetic Programming (GP) is that evolved expressions appear to
drift towards large and slow forms on average. This report presents a novel analysis of the role
played b... / such as a belief network or a neural network. Thus evolved programs are br decision trees or sigma-pi neural networks rather than An
2246.0 Combining Simulated Annealing with Local Search Heuristics - Martin, Otto (1996)(Correct)
We introduce a meta-heuristic to combine simulated annealing with local search methods
for CO problems. This new class of Markov chains leads to significantly more powerful
optimization methods than e... / genetic algorithms and neural network approaches The present br In J. Denker editor Neural Networks for Computing . AIP
2245.2 Feature Selection via Mathematical Programming - Bradley, Mangasarian, Street (1997)(Correct)
The problem of discriminating between two finite point sets in n-dimensional feature space by
a separating plane that utilizes as few of the features as possible, is formulated as a mathematical
progr... / OBD method for reducing neural network complexity. One feature br of mathematical programming to neural networks are given in We
2244.5 Transfer of learning in backpropagation and in related neural network .. - Murre(Correct)
this paper. After evaluating some of these limits, as well as some of the
advantages, we present a number of simulations investigating interference and transfer of
human learning. It will be shown tha... / backpropagation and in related neural network models Jacob M.J. Murre br Given the range of neural network paradigms available at the
2244.2 Bayes Optimal Instance-Based Learning - Kontkanen, Myllymäki, al. (1998)(Correct)
In this paper we present a probabilistic formalization of the
instance-based learning approach. In our Bayesian framework, moving
from the construction of an explicit hypothesis to a data-driven ins... / include the set of feedforward neural network models the set of Bayesian br include the set of feedforward neural network models the set of Bayesian
2242.4 Independent Component Analysis Using an Extended Infomax Algorithm.. - Lee (1997)(Correct)
An extension of the infomax algorithm of Bell and Sejnowski (1995) is presented that is able to blindly separate mixed signals with sub- and super-Gaussian source distributions. This was achieved by u... / studied by many researchers in neural networks and statistical signal br in a single-layer feedforward neural network. The algorithm is effective in
2239.1 Prediction of O-glycosylation of mammalian proteins: Specificity.. - Hansen, Lund, Engelbrecht, Bohr..(Correct)
The specificity of the enzyme(s) catalyzing the covalent link between the hydroxyl side-chains
of serine or threonine and the sugar moiety GalNAc is unknown. Pattern recognition by artificial
neural n... / recognition by artificial neural networks and weight matrix algorithms br sequence acceptor patterns. The neural networkswere trained on the hitherto
2236.3 Development of An Approach to Language Identification based on.. - Yonghong Yan (1995)(Correct)
xii
1 Introduction 1
1.1 Background : : : : : : : : : : : : : : : : : : : : : : : : : : : : : : : : : : : : 2
1.1.1 Nature of the Problem : : : : : : : : : : : : : : : : : : : : : : : : : : 2
1.1.2 T... / . . Baseline System with a neural network as the Final Classifier br . Neural network as the final classifier
2229.4 Fast and Robust Fixed-Point Algorithms for Independent Component.. - Hyvärinen (1999)(Correct)
Independent component analysis (ICA) is a statistical method for transforming an observed multidimensional random vector into components that are statistically as independent from each other as possib... / To appear in IEEE Trans. on Neural Networks January Abstract br A central problem in neural network research as well as in
2224.2 Biomimetic Navigation Models and Strategies in Animats - Trullier, Meyer (1997)(Correct)
This paper describes a hierarchy of four navigation strategies --- guidance,
place recognition-triggered response, topological navigation and metric navigation.
Such a hierarchy can be used to categor... / a -layer feedforward neural network Figure that largely br of their place fields. The neural network also models experimental data
2217.4 Deliverable R3--B4--P Task B4 : Benchmarks - Covering The(Correct)
This report is the
result of a strong cooperation between all partners of the project. The different topics
of the benchmarking methodology have been the subject of several useful discussions
during t... / to the benchmarking studies of neural network classification algorithms br are are well known by the neural network and machine learning
2208.2 A System Identification Software Tool for General MISO ARX-type of.. - Lindskog (1996)(Correct)
The typical system identification procedure requires powerful and versatile software
means. In this paper we describe and exemplify the use of a prototype identification software
tool, applicable fo... / structures feed-forward neural networks radial basis function br standard feed-forward neural networks feed-forward
2207.2 Face Recognition Under Varying Pose - Beymer (1993)(Correct)
Researchers in computer vision and pattern recognition have worked on automatic techniques for recognizing
human faces for the last 20 years. While some systems, especially template-based ones, have b... / of hidden layer nodes in neural networks Vincent Waite and br typical matching metric. The neural network approaches construct a
2206.9 Learning to Perceive the World as Articulated: An Approach for.. - Tani, Nolfi (1998)(Correct)
This paper describes how agents can learn an internal model of the world
structurally by focusing on the problem of behavior-based articulation. We develop
an on-line learning scheme -- the so-called ... / version is in press. in Neural Networks Special Issue . br types of approach. One is the neural network learning approach. Krose and
2200.1 Bayesian Invariant Measurements of Generalisation for Continuous.. - Zhu, Rohwer (1995)(Correct)
A family of measurements of generalisation is proposed for estimators of continuous
distributions. In particular, they apply to neural network learning rules
associated with continuous neural networks... / In particular they apply to neural network learning rules associated br associated with continuous neural networks. The optimal estimators
2195.9 Stimulus dependent correlations in stochastic networks - Kappen (1997)(Correct)
It has been observed that cortical neurons display synchronous firing
for some stimuli and not for others. The resulting synchronous cell assemblies
are thought to form the basis of object perception.... / The proposed Boltzmann Machine neural network is the simplest artificial br is usually done in attractor neural networks Those analyses are
2189.1 BISMARC: A Biologically Inspired System for Map-based Autonomous.. - Huntsberger, Rose (1998)(Correct)
As the complexity of the missions to planetary surfaces increases, so too does the
need for autonomous rover systems. This need is complicated by the power, mass
and computer storage restrictions on s... / hippocampal maps wavelets neural networks . INTRODUCTION The br There are also a number of neural network approaches that have been used
2177.2 Learning Navigational Behaviors using a Predictive Sparse Distributed .. - Rao, Fuentes (1996)(Correct)
We describe a general framework for the acquisition
of perception-based navigational behaviors in autonomous
mobile robots. A self-organizing sparse distributed
memory equivalent to a three-layered ne... / equivalent to a three-layered neural network is used to learn the desired br used for this purpose including neural networks evolutionary
2174.5 Learning long-term dependencies in NARX recurrent neural networks - Lin, Horne, Tino, Giles (1996)(Correct)
It has recently been shown that gradient-descent learning algorithms for recurrent neural
networks can perform poorly on tasks that involve long--term dependencies, i.e. those problems
for which the d... / dependencies in NARX recurrent neural networks Tsungnan Lin br algorithms for recurrent neural networks can perform poorly on tasks
2171.6 GA-easy and GA-hard Constraint Satisfaction Problems - Eiben, Raué, Ruttkay (1995)(Correct)
In this paper we discuss the possibilities of applying genetic
algorithms (GA) for solving constraint satisfaction problems (CSP). We
point out how the greediness of deterministic classical CSP solvin... / in a local optimum. In a neural network was presented to solve CSPs br M. D.A discrete stochastic neural network algorithm for constraint
2159.6 New Neural Transfer Functions - Duch, Jankowski (1997)(Correct)
this article advantages of various neural transfer functions are discussed
and several new type of functions are introduced. Universal transfer
functions, parametrized to change from localized to delo... / choice of transfer functions in neural networks is of crucial importance to br functions in many types of neural networks such as RBF RAN FSM and
2155.2 An incremental approach to developing intelligent neural network.. - Meeden (1995)(Correct)
By beginning with simple reactive behaviors and gradually building up to more memorydependent
behaviors, it may be possible for connectionist systems to eventually achieve the
level of planning. This ... / to developing intelligent neural network controllers for robots Lisa br These methods are applied to a neural network controller for a simple
2152.2 Graphical Models for Discovering Knowledge - Buntine (1995)(Correct)
There are many different ways of representing knowledge, and for each of these ways there are many different discovery algorithms. How can we compare different representations? How can we mix, match a... / unsupervised learning systems neural networks and many hybrids. ffl br model such as the weights in a neural network the standard deviation of a
2146.5 Implementation of Sparse Neural Networks on Fixed Size Arrays - Misra, Kumar (1991)(Correct)
Recent research in Artificial Neural Networks (ANN's) has shown that ANN's
will play an important role in solving many signal processing problems. To fully
capture the potential that this new computat... / Implementation of Sparse Neural Networks on Fixed Size Arrays br Recent research in Artificial Neural Networks ANN's has shown that ANN's