Home     Top: Artificial Intelligence: Optimization    [Expert Systems   Knowledge Representation   Natural Language Processing   Optimization   Planning   Robotics]

Change ordering:   Authority   Hubs (tutorials)   Date   Expected authority       Show titles only
Ordered by the number of citations

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.

373   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... / a more recent method in convex optimization. They also show that every br add a penalty to the optimization to encourage exploring broad

132   Noise Strategies for Improving Local Search - Selman, Kautz, Cohen (1994)   (Correct)
It has recently been shown that local search is surprisingly good at finding satisfying assignments for certain computationally hard classes of CNF formulas. The performance of basic local search meth... / successfully applied to many optimization problems. Hansen and Jaumard br approach in combinatorial optimization of terminating the search when

131   BIRCH: An Efficient Data Clustering Method for Very Large Databases - Zhang, Ramakrishnan, Livny (1996)   (Correct)
Finding useful patterns in large datasets has attracted considerable interest recently, and one of the most widely studied problems in this area is the identification of clusters, or densely populated... / is a nonconvex discrete KR optimization problem. Due to an abundance br extremely small. Iterative optimization IO DH KR starts with

128   Performance of Dynamic Load Balancing Algorithms for Unstructured.. - Williams (1991)   (Correct)
If a finite element mesh has a sufficiently regular structure, it is easy to decide in advance how to distribute the mesh among the processors of a distributed-memory parallel processor, but if the me... / than many small messages. This optimization problem for the mesh br types depending on when the optimization is made and whether the cost

79   A New Method for Mapping Optimization Problems onto Neural Networks - Peterson, Söderberg (1989)   (Correct)
A novel modified method for obtaining approximate solutions to difficult optimization problems within the neural network paradigm is presented. We consider the graph partition and the travelling sal... / A New Method for Mapping Optimization Problems onto Neural Networks br solutions to difficult optimization problems within the neural

76   Local Search Strategies for Satisfiability Testing - Selman (1996)   (Correct)
It has recently been shown that local search is surprisingly good at finding satisfying assignments for certain classes of CNF formulas (Selman et al. 1992). In this paper we demonstrate that the pow... / successfully applied to many optimization problems. Hansen and Jaumard br approach in combinatorial optimization of terminating the search when

73   The Reactive Tabu Search - Battiti (1994)   (Correct)
this paper the concept of chaotic attractor is used only as an example of a dynamic behavior that could affect the search process, we summarize the main characteristics and refer to [13] for a detaile... / an algorithm for combinatorial optimization where an explicit check for br scheme for combinatorial optimization that combines a hill-climbing

63   A Review of Evolutionary Artificial Neural Networks - Yao (1993)   (Correct)
Research on potential interactions between connectionist learning systems, i.e., artificial neural networks (ANNs), and evolutionary search procedures, like genetic algorithms (GAs), has attracted a l... / the rapid generation and optimisation of tightly pruned interesting br The shift from the direct optimisation of connectivity patterns to the

61   An Evolutionary Algorithm that Constructs Recurrent Neural Networks - Angeline, Saunders, Pollack (1994)   (Correct)
Standard methods for inducing both the structure and weight values of recurrent neural networks fit an assumed class of architectures to every task. This simplification is necessary because the intera... / to perform well at function optimization. Section argues that this br Genetic Algorithms in Search Optimization and Machine Learning. Addison

57   Improving Regression Estimation: Averaging Methods for Variance.. - Perrone (1993)   (Correct)
Perrone, M. P. and N. Intrator (1992) Unsupervised Splitting Rules for Neural Tree Classifiers. Proceedings of the International Joint Conference on Neural Networks pp. III:820-825. Perrone, M. P.,... / to General Convex Measure Optimization by Michael Peter Perrone B. br Extensions to Convex Optimization . Introduction

55   A Multiscale Random Field Model for Bayesian Image Segmentation - Bouman, Shapiro (1996)   (Correct)
Many approaches to Bayesian image segmentation have used maximum a posteriori (MAP) estimation in conjunction with Markov random fields (MRF). While this approach performs well, it has a number of dis... / criteria results in a series of optimization steps going from coarse to br This is done by solving the optimization problem x arg min x

50   The Geometry Of Algorithms With Orthogonality Constraints - Edelman, Arias, Smith (1998)   (Correct)
In this paper we develop new Newton and conjugate gradient algorithms on the Grassmann and Stiefel manifolds. These manifolds represent the constraints that arise in such areas as the symmetric eige... / quotient iteration eigenvalue optimization sequential quadratic br ideas from different areas. The optimization community has long recognized

47   Competitive Environments Evolve Better Solutions for Complex Tasks - Angeline, Pollack (1993)   (Correct)
In the typical genetic algorithm experiment, the fitness function is constructed to be independent of the contents of the population to provide a consistent objective measure. Such objectivity entails... / solutions for many simple optimization problems it is often br Genetic Algorithms in Search Optimization and Machine Learning

47   A graduated assignment algorithm for graph matching - Gold, Rangarajan (1996)   (Correct)
A graduated assignment algorithm for graph matching is presented which is fast and accurate even in the presence of high noise. By combining graduated non-convexity (deterministic annealing), two-way ... / approach employs nonlinear optimization methods or heuristic br search methods. Other nonlinear optimization approaches are neural

47   An Empirical Study of Algorithms for Point-Feature Label Placement - Christensen, Marks, Shieber (1995)   (Correct)
A major factor affecting the clarity of graphical displays that include text labels is the degree to which labels obscure display features (including other labels) as a result of spatial overlap. Poin... / as a type of combinatorial optimization problem. Complexity analysis br be thought of as a combinatorial optimization problem. Like all such

42   Feature Subset Selection Using A Genetic Algorithm - Yang (1997)   (Correct)
this paper. See [1] for a more complete list of references). Some of these involve searching for an optimal subset of features based on some criteria of interest. Feature weighting is a variant of fea... / an instance of a multi-criteria optimization problem. The multiple criteria br approach for multicriteria optimization. This paper explores a

39   Gradient Flows and Geometric Active Contour Models - Kichenassamy, Kumar, Olver.. (1994)   (Correct)
In this note, we analyze the geometric active contour models proposed in [10, 31] from a curve evolution point of view and propose some modifications based on gradient flows relative to certain new me... /

38   Region Competition: Unifying Snakes, Region Growing, and Bayes/MDL.. - Zhu (1996)   (Correct)
We present a novel statistical and variational approach to image segmentation based on a new algorithm named region competition. This algorithm is derived by minimizing a generalized Bayes/MDL criteri... / and iv Global optimization approaches based on energy br algorithm from a global optimization criterion. Then we show how

38   A Comprehensive Survey of Evolutionary-Based Multiobjective.. - Coello (1998)   (Correct)
This paper presents a critical review of the most important evolutionary-based multiobjective optimization techniques developed over the years, emphasizing the importance of analyzing their Operatio... / Multiobjective Optimization Techniques Carlos A. Coello br multiobjective optimization techniques developed over the

38   Bead: Explorations in Information Visualization - Chalmers, Chitson (1992)   (Correct)
We describe work on the visualization of bibliographic data and, to aid in this task, the application of numerical techniques for multidimensional scaling. Many areas of scientific research involve co... / retrieval numerical optimization and computational physics. br the configuration task as an optimization problem. This has allowed the

38   Region Competition: Unifying Snakes, Region Growing, and Bayes/MDL.. - Zhu (1995)   (Correct)
We present a novel statistical and variational approach to image segmentation based on a new algorithm named region competition. This algorithm is derived by minimizing a generalized Bayes/MDL(Minimum... / and iv Global optimization approaches based on energy br derive our theory from the MDL optimization criterion then we show how

35   On the Applications of Harmonic Functions to Robotics - Connolly, Grupen (1993)   (Correct)
Harmonic functions are solutions to Laplace's equation. Such functions can be used to advantage for potential-field path planning, since they do not exhibit spurious local minima. Harmonic functions a... / they do not exhibit spurious local minima. Harmonic functions are shown br the spontaneous creation of minima other than the goal. The robot

33   A New Merit Function For Nonlinear Complementarity Problems And A.. - Facchinei, Soares (1997)   (Correct)
We investigate the properties of a new merit function which allows us to reduce a nonlinear complementarity problem to an unconstrained global minimization one. Assuming that the complementarity pro... / showed to be relevant to optimization algorithms. Recently the br play an important role in many optimization problems. Under very mild

30   Object-Centered Surface Reconstruction: Combining Multi-Image Stereo.. - Fua, Leclerc (1995)   (Correct)
Our goal is to reconstruct both the shape and reflectance properties of surfaces from multiple images. We argue that an object-centered representation is most appropriate for this purpose because it n... / described below in which the optimization procedure dynamically adapts br a computationally effective optimization procedure and have

30   Autocalibration from Planar Scenes - Triggs (1998)   (Correct)
This paper describes a theory and a practical algorithm for the autocalibration of a moving projective camera, from m 5 views of a planar scene. The unknown camera calibration, and (up to scale) the ... / model to initialize the optimization from a minimal algebraic br to use except that constrained optimization is required to handle the rank

30   An experimental comparison of several clustering and initialization.. - Melia (1998)   (Correct)
Data clustering is an important technique for exploratory data analysis, and has been studied for several years. It has been shown to be useful in many practical domains such as data classification ... / it is a nonconvex discrete optimization problem. Due to an br vectors during the codebook optimizations at all the codebook size

27   Genetic Local Search for the TSP: New Results - Merz, Freisleben (1997)   (Correct)
The combination of local search heuristics and genetic algorithms has been shown to be an effective approach for finding near-optimum solutions to the traveling salesman problem. In this paper, previo... / the best-known combinatorial optimization problems. It has attracted br Contest on Evolutionary Optimization held as part of the

27   Neural Networks for Optimal Approximation of Smooth and Analytic.. - Mhaskar (1996)   (Correct)
We prove that neural networks with a single hidden layer are capable of providing an optimal order of approximation for functions assumed to possess a given number of derivatives, if the activation ... / are extremely simple use no optimization and avoid all the problems br associated with the classical optimization-based training paradigms such

26   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... / of a network can be seen as an optimization process with the goal to find br algorithms compared to other optimization methods is that heuristics can

26   MIMIC: Finding Optima by Estimating Probability Densities - De Bonet, Isbell, Jr., Viola (1996)   (Correct)
In many optimization problems, the structure of solutions reflects complex relationships between the different input parameters. For example, experience may tell us that certain parameters are closely... / MA Abstract In many optimization problems the structure of br the global structure of the optimization landscape. A novel and

26   A New Approach to Effective Circuit Clustering - Hagen, Kahng (1992)   (Correct)
The complexity of next-generation VLSI systems will exceed the capabilities of top-down layout synthesis algorithms, particularly in netlist partitioning and module placement. Bottom-up clustering is ... / becomes tractable to existing optimization methods. In this paper we br interchange or quadratic optimization via relaxation or

24   Evolving Artificial Neural Networks - Yao (1999)   (Correct)
Learning and evolution are two fundamental forms of adaptation. There has been a great interest in combining learning and evolution with artificial neural networks (ANNs) in recent years. This paper (... / ANNs and EAs for combinatorial optimization will be mentioned but not br data. A gradient descent-based optimization algorithm such as

24   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... / a challenging multi-criterion optimization problem namely that of br D. Genetic Algorithms in Search Optimization and Machine Learning. Reading

21   A Discrete Lagrangian-Based Global-Search Method for Solving.. - Wah, Shang (1998)   (Correct)
Satisfiability is a class of NP-complete problems that model a wide range of real-world applications. These problems are difficult to solve because they have many local minima in their search space, o... / constrained or unconstrained optimization problems. In Section we br as a discrete constrained optimization problem with a goal of

21   A Genetic Local Search Algorithm for Solving Symmetric and Asymmetric .. - Freisleben, Merz (1996)   (Correct)
The combination of local search heuristics and genetic algorithms is a promising approach for finding nearoptimum solutions to the traveling salesman problem (TSP). In this paper, an approach is prese... / testbed for combinatorial optimization methods which attempt to find br at various steps of the GA optimization process. The proposed

20   A Fast Adaptive Layout Algorithm for Undirected Graphs (Extended.. - Frick, Ludwig, Mehldau (1994)   (Correct)
and System Demonstration) Arne Frick ? , Andreas Ludwig, Heiko Mehldau Universitat Karlsruhe, Fakultat fur Informatik, D-76128 Karlsruhe, Germany Abstract. We present a randomized adaptive layout a... / art. Even more so simultaneous optimization for several criteria can br to the simultaneous optimization problem in Sect. . We

20   Subdivision Direction Selection In Interval Methods For Global.. - Csendes (1997)   (Correct)
The role of the interval subdivision selection rule is investigated in branch-and-bound algorithms for global optimization. The class of rules that allow convergence for the model algorithm is chara... / In Interval Methods For Global Optimization T. Csendes Y And D. br algorithms for global optimization. The class of rules that allow

20   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... / in favor of alternative optimization methods However the br described in This problem is a minimal task designed as a test that

19   Comparative Bibliography of Ontogenic Neural Networks - Fiesler (1994)   (Correct)
This document will be published in: Proceedings of the International Conference on Artificial Neural Networks (ICANN '94). until it is large enough to handle the problem (or to eliminate possible lo... / generalization implementation optimization size and or execution speed br speed and the avoidance of local minima. Possible topology modifications

19   Initialization of Iterative Refinement Clustering Algorithms - Fayyad, Reina, Bradley (1998)   (Correct)
Iterative refinement clustering algorithms (e.g. K-Means, EM) converge to one of numerous local minima. It is known that they are especially sensitive to initial conditions. We present a procedure for... / pattern recognition DH F optimization BMS SI and statistics br given as input. The clustering optimization problem is that of finding

19   Dynamic Euclidean Minimum Spanning Trees and Extrema of Binary.. - Eppstein (1995)   (Correct)
We maintain the minimum spanning tree of a point set in the plane, subject to point insertions and deletions, in amortized time O(n 1/2 log 2 n) per update operation. We reduce the problem to maintain... / been studied for many geometric optimization problems including closest br and many similar geometric optimization problems. Dobkin and Suri call

18   Search-Intensive Concept Induction - Giordana (1995)   (Correct)
This paper describes REGAL, a distributed genetic algorithm-based system, designed for learning First Order Logic concept descriptions from examples. The system is a hybrid between Pittsburgh's and Mi... / successfully applied mainly to optimization problems also machine br functions to a set of benchmark optimization problems Deb and Goldberg

18   On The Problem Of Local Minima In Backpropagation - Gori, Tesi (1992)   (Correct)
Supervised Learning in Multi-Layered Neural Networks (MLNs) has been recently proposed through the well-known Backpropagation algorithm. This is a gradient method which can get stuck in local minima, ... / gradient methods for nonlinear optimization Proceedings of the first br On The Problem Of Local Minima In Backpropagation M. Gori And A.

17   Using Genetic Algorithms for Robot Motion Planning - Ahuactzin, Talbi, Bessiere, Mazer (1992)   (Correct)
We present an ongoing research work on robot motion planning using genetic algorithms. Our goal is to use this technique to build fast motion planners for robot with six or more degree of freedom. A... / problem can be expressed as an optimization problem and thus solved with a br Genetic algorithms in search optimization and machine learning The

17   Design Of Multi-Dimensional Derivative Filters - Simoncelli (1994)   (Correct)
Many multi-dimensional signal processing problems require the computation of signal gradients or directional derivatives. Traditional derivative estimates based on adjacent or central differences are ... / analytically and avoid complex optimization procedures that may get stuck br methods with local optimization. IEEE Pat. Anal. Mach.

17   Learning Rate Schedules For Faster Stochastic Gradient Search - Darken, Chang, Moody (1992)   (Correct)
Stochastic gradient descent is a general algorithm that includes LMS, on-line backpropagation, and adaptive k-means clustering as special cases. The standard choices of the learning rate j (both ada... / techniques for solving optimization problems Ljung and Soderstrom br of ff by performing a second optimization. However here we take a more

17   Conformal curvature flows: from phase transitions to active vision - Kichenassamy, Kumar (1995)   (Correct)
In this paper, we analyze geometric active contour models from a curve evolution point of view and propose some modifications based on gradient flows relative to certain new feature-based Riemannian m... / briefly sketch the energy based optimization approach to deformable br constrained version of the given optimization problem and so derive a

17   Evolutionary Artificial Neural Networks - Yao (1993)   (Correct)
Evolutionary Artificial Neural Networks (EANNs) can be considered as a combination of artificial neural networks (ANNs) and evolutionary search procedures, such as genetic algorithms (GAs). This paper... / facilitate rapid generation and optimisation of tightly pruned interesting br The shift from the direct optimisation of architectures to the

16   Global Optimization for Neural Network Training - Shang (1996)   (Correct)
In this paper, we study various supervised learning methods for training feed-forward neural networks. In general, such learning can be considered as a nonlinear global optimization problem in which t... / Global Optimization for Neural Network Training br considered as a nonlinear global optimization problem in which the goal is

16   Further Experience with Controller-Based Automatic Motion Synthesis.. - Auslander, Fukunaga, Partovi.. (1995)   (Correct)
We extend an earlier automatic motion-synthesis algorithm for physically realistic articulated figures in several ways. First, we summarize several incremental improvements to the original algorithm t... / machine learning stochastic optimization evolutionary computation. br motion synthesis uses local optimization to refine initial

16   Refining Initial Points for K-Means Clustering - Bradley, Fayyad (1998)   (Correct)
Practical approaches to clustering use an iterative procedure (e.g. K-Means, EM) which converges to one of numerous local minima. It is known that these iterative techniques are especially sensitive t... / pattern recognition DH F optimization BMS SI and statistics br given as input. The clustering optimization problem is that of finding

16   Weak Sharp Minima In Mathematical Programming - Burke, Ferris (1993)   (Correct)
The notion of a sharp, or strongly unique, minimum is extended to include the possibility of a nonunique solution set. These minima will be called weak sharp minima. Conditions necessary for the sol... / be applied to convex composite optimization problems to establish the br this we consider the related optimization problem minimize hx Mx

16   A Continuous Approach to Inductive Inference - Kamath (1992)   (Correct)
In this paper we describe an interior point mathematical programming approach to inductive inference. We list several versions of this problem and study in detail the formulation based on hidden Boole... / inference is in fact an optimization problem where one wants to br are many ways to formalize this optimization problem. In this paper we

16   Adaptive Global Optimization with Local Search - Hart (1994)   (Correct)
xiv I Introduction : : : : : : : : : : : : : : : : : : : : : : : : : : : : : : : : : : 1 A. Global Optimization : : : : : : : : ... / San Diego Adaptive Global Optimization With Local Search A br A. Global Optimization

15   Neural Networks for Optimization Problems with Inequality Constraints .. - Ohlsson, Peterson, Söderberg (1993)   (Correct)
A strategy for finding approximate solutions to discrete optimization problems with inequality constraints using mean field neural networks is presented. The constraints x 0 are encoded by x\Theta(x... / TP - Neural Networks for Optimization Problems with Inequality br solutions to discrete optimization problems with inequality

15   New Genetic Local Search Operators for the Traveling Salesman Problem - Freisleben, Merz (1996)   (Correct)
In this paper, an approach is presented to incorporate problem specific knowledge into a genetic algorithm which is used to compute near-optimum solutions to traveling salesman problems (TSP). The a... / NP-hard combinatorial optimization problem in which a br methods useful in a variety of optimization problems such as simulated

15   Synthesis and Performance Analysis of Multilayer Neural Network.. - Schiffmann, Joost, Werner (1992)   (Correct)
this paper we present various approaches for automatic topology--optimization of backpropagation networks. First of all, we review the basics of genetic algorithms which are our essential tool for a t... / . GAs for topology optimization br for automatic topology-optimization of backpropagation networks.

15   A hierarchical statistical framework for the segmentation of.. - Kervrann, Heitz (1993)   (Correct)
In this paper, we propose a new statistical framework for modeling and extracting 2D moving deformable objects from image sequences. The object representation relies on a hierarchical description of... / procedures. The use of global optimization algorithms yields robust and br bayesian estimation global optimization motion segmentation

15   Fast Approximate Energy Minimization via Graph Cuts - Boykov, Veksler (1999)   (Correct)
Many tasks in computer vision involve assigning a label (such as disparity) to every pixel. A common constraint is that the labels should vary smoothly almost everywhere. These tasks are naturally sta... / on graph cuts as a powerful optimization technique. An important br to solving a known combinatorial optimization problem called the minimum

14   Registering Multiview Range Data to Create 3D Computer Objects - Blais, Levine (1993)   (Correct)
This research deals with the problem of range image registration for the purpose of building surface models of three-dimensional objects. The registration task involves finding the translation and rot... / the registration task as an optimization problem. We define a function br space. A stochastic optimization technique Very Fast Simulated

14   Bilevel and Multilevel Programming: A Bibliography Review - Vicente, Calamai (1994)   (Correct)
This paper contains a bibliography of all references central to bilevel and multilevel programming that the authors know of. It should be regarded as a dynamic and permanent contribution since, all... / problems hierarchical optimization minimax problems. AMS br historical notes Multilevel optimization problems are mathematical

14   Bayesian Training of Backpropagation Networks by the Hybrid Monte.. - Neal (1993)   (Correct)
It is shown that Bayesian training of backpropagation neural networks can feasibly be performed by the "Hybrid Monte Carlo" method. This approach allows the true predictive distribution for a test c... / conventional training is an optimization problem Bayesian training and br many modes has been found by an optimization procedure If one also

14   Isotropic Effective Energy Simulated Annealing Searches for Low.. - Coleman, Shalloway, Wu (1993)   (Correct)
The search for low energy states of molecular clusters is associated with the study of molecular conformation and especially protein folding. This paper describes a new global minimization algorithm... / in the area of numerical optimization. A number of approaches br to global and combinatorial optimization. Since then the algorithm has

14   A Motion Planning Based Approach for Inverse Kinematics of Redundant.. - Ahuactzin, al. (1997)   (Correct)
We propose a new approach to solving the point-topoint inverse kinematics problem for highly redundant manipulators. It is inspired by recent motion planning research and explicitly takes into account... / path is found more elaborate optimization criteria can then be used to br inverse kinematic problem as an optimization problem as is normally done in

14   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) [... / the Baldwin effect and function optimization in Parallel Problem br Y. Shang and B. Wah Global optimization for neural network training

13   The Dynamics of a Genetic Algorithm under Stabilizing Selection - Rattray (1996)   (Correct)
A formalism recently introduced by Prugel-Bennett and Shapiro uses the methods of statistical mechanics to model the dynamics of genetic algorithms. To be of more general interest this formalism must ... / which is a combinatorial optimization problem with a strongly br to a harder combinatorial optimization problem subset sum. Although

13   Cost Versus Distance In the Traveling Salesman Problem - Boese (1995)   (Correct)
This paper studies the distribution of good solutions for the traveling salesman problem (TSP) on a well-known 532-city instance that has been solved optimally by Padberg and Rinaldi [16]. For each of... / multi-start strategy for global optimization called Adaptive Multi-Start br to combinatorial global optimization problems. In global

13   Local Verification of Global Integrity Constraints in Distributed.. - Gupta, Widom (1993)   (Correct)
We present an optimization for integrity constraint verification in distributed databases. The optimization allows a global constraint, i.e. a constraint spanning multiple databases, to be verified by... / Abstract We present an optimization for integrity constraint br in distributed databases. The optimization allows a global constraint

13   Algebraic Transformations of Objective Functions - Mjolsness, Garrett (1994)   (Correct)
Many neural networks can be derived as optimization dynamics for suitable objective functions. We show that such networks can be designed by repeated transformations of one objective into another wit... / networks can be derived as optimization dynamics for suitable br trajectory followed during optimization. We do not require that the

13   An Improved Worst-Case to Average-Case Connection for Lattice.. - Cai, Nerurkar (1997)   (Correct)
We improve a connection of the worst-case complexity and the average-case complexity of some well-known lattice problems. This fascinating connection was first discovered by Ajtai [1] in 1996. We impr... / approximation and combinatorial optimization integer programming br Algorithms and Combinatorial Optimization. Springer Verlag .

13   New NCP-Functions and Their Properties - Kanzow, Yamashita, Fukushima (1997)   (Correct)
Recently, Luo and Tseng proposed a class of merit functions for the nonlinear complementarity problem (NCP) and showed that it enjoys several interesting properties under some assumptions. In this p... / merit function unconstrained optimization reformulation error bound br can be cast as the unconstrained optimization problem with the objective

13   Object Pose from 2-D to 3-D Point and Line Correspondences - Phong, Horaud, Yassine, Tao (1995)   (Correct)
In this paper we present a method for optimally estimating the rotation and translation between a camera and a 3-D object from point and/or line correspondences. First we devise an error function and ... / aspects of a trust-region optimization method. This method compares br Levenberg-Marquardt non-linear optimization method. Finally we present some

13   A Fast Stochastic Error-Descent Algorithm for Supervised Learning and .. - Cauwenberghs (1993)   (Correct)
A parallel stochastic algorithm is investigated for error-descent learning and optimization in deterministic networks of arbitrary topology. No explicit information about internal network structure ... / for Supervised Learning and Optimization Gert Cauwenberghs br for error-descent learning and optimization in deterministic networks of

13   Algorithmic Geometry of Numbers - Kannan (1987)   (Correct)
this article - Algorithmic Geometry of Numbers. The fundamental basis reduction algorithm of Lov'asz which first appeared in Lenstra, Lenstra, Lov'asz [46] was used in Lenstra's algorithm for integer ... / programming and other discrete optimization problems which seem inherently br The integer programming optimization problem is the problem of

13   Supply and Threshold Voltage Scaling for Low Power CMOS - Gonzalez (1997)   (Correct)
This paper investigates the effect of lowering the supply and threshold voltages on the energy efficiency of CMOS circuits. Using a first-order model of the energy and delay of a CMOS circuit, we show... / at both energy and delay during optimization and use the energy-delay br thus one wants to operate near the minima but gates at this point are

13   A Parallel Build-Up Algorithm for Global Energy Minimizations of.. - Coleman, Shalloway, Wu (1993)   (Correct)
This work studies the build-up method for the global minimization problem for molecular conformation, especially protein folding. The problem is hard to solve for large molecules using general minim... / in the area of numerical optimization. Many approaches have been br Smith Parallel Global Optimization Numerical Methods Dynamic

12   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... / supervised learning as an optimization problem in the joint space of br obtained by maximizing The optimization problem arising from this

12   A Review Of Techniques In The Verified Solution Of Constrained Global .. - Kearfott (1996)   (Correct)
Elements and techniques of state-of-the-art automatically verified constrained global optimization algorithms are reviewed, including a description of ways of rigorously verifying feasibility for equa... / Solution Of Constrained Global Optimization Problems R. Baker Kearfott br verified constrained global optimization algorithms are reviewed

12   Conformational analysis of molecular chains using Nano-Kinematics - Manocha (1995)   (Correct)
We present algorithms for 3-D manipulation and conformational analysis of molecular chains, when bond length, bond angles and related dihedral angles remain fixed. These algorithms are useful for lo... / are based on stochastic optimization and Monte Carlo analysis br on numerical techniques like optimization or Newton's method to the

12   Analysis of Heuristic Methods for Partial Constraint Satisfaction.. - Wallace (1996)   (Correct)
Problems that do not have complete solutions occur in many areas of application of constraint solving. Heuristic repair methods that have been used successfully on complete CSPs can also be used on ... / MAX-CSPs. Since these are optimization problems the basic question is br L. A. McGeoch and C. Shevon. Optimization by simulated annealing An

12   Training Neural Nets with the Reactive Tabu Search - Battiti, Tecchiolli (1995)   (Correct)
In this paper the task of training sub-symbolic systems is considered as a combinatorial optimization problem and solved with the heuristic scheme of the Reactive Tabu Search (RTS) proposed by the aut... / is considered as a combinatorial optimization problem and solved with the br Tabu Search. An iterative optimization process based on a modified

12   Differential Evolution - A simple and efficient adaptive scheme for.. - Storn, Price (1995)   (Correct)
A new heuristic approach for minimizing possibly nonlinear and non differentiable continuous space functions is presented. By means of an extensive testbed, which includes the De Jong functions, it wi... / adaptive scheme for global optimization over continuous spaces by br Problems which involve global optimization over continuous spaces are

12   Reactive Search: Toward Self-Tuning Heuristics - Battiti (1996)   (Correct)
Local (neighborhood) search can be guided to go beyond local minima through metaheuristic methods that use the information obtained in the previous part of the run. The Reactive Search (RS) method pro... / in heuristics for discrete optimization problems. RS belongs to the br basin lose any interest for optimization. The search should avoid

12   Preference Logic Programming - Govindarajan (1995)   (Correct)
This research is concerned with the semantics, applications, and implementation of a declarative language for specifying constraint optimization and relaxation problems. These problems arise in divers... / for specifying constraint optimization and relaxation problems. These br how to formulate constraint optimization problems as well as heuristics

12   A Semismooth Newton Method For Variational Inequalities: Theoretical.. - Facchinei, Fischer, Kanzow (1997)   (Correct)
Variational inequalities over sets defined by systems of equalities and inequalities are considered. A continuously differentiable merit function is proposed whose unconstrained minima coincide with... / condition of the constrained optimization problem min f x s.t. x br concentrated on the so called optimization approach in which the

12   Alopex: A Correlation-Based Learning Algorithm for Feed-Forward and.. - Unnikrishnan, Venugopal (1994)   (Correct)
e present a learning algorithm for neural networks, called Alopex. Instead of a error gradient, Alopex uses local correlations between changes in individual weights nd changes in the global error mea... / for solving combinatorial optimization problems Harth Pandya br neural network is treated as an optimization problem. The objec- a

12   Global Optimization For The Phase Stability Problem - M.Mcdonald   (Correct)
The Gibbs tangent plane criterion has become an important tool in determining the quality of obtained solutions to the phase and chemical equilibrium problem. The ability to determine if a postulated ... / Global Optimization For The Phase Stability br The advantage of a global optimization approach is that if a

11   Acyclic Multi-Way Partitioning of Boolean Networks - Jason Cong (1994)   (Correct)
Acyclic partitioning on combinational boolean networks has wide range of applications, from multiple FPGA chip partitioning to parallel circuit simulation. In this paper, we present two efficient algo... / final design for performance optimization. Partitioning based logic br also supports a number of optimizations to reduce both checkpointing

11   Trace-Based Methods for Solving Nonlinear Global Optimization and.. - Wah, Chang (1996)   (Correct)
In this paper we present a method called NOVEL (Nonlinear Optimization via External Lead) for solving continuous and discrete global optimization problems. NOVEL addresses the balance between global... / Journal of Global Optimization - c fl Kluwer br for Solving Nonlinear Global Optimization and Satisfiability Problems

11   A Local Search Template - Vaessens, Aarts, Lenstra (1992)   (Correct)
A template is presented that captures a vast majority of the local search algorithms proposed in the literature, including iterative improvement, simulated annealing, threshold accepting, tabu search,... / approximate solutions to hard optimization problems. The basic idea is to br Preliminaries An optimization problem is either a

11   A Genetic Local Search Approach to the Quadratic Assignment Problem - Merz, Freisleben (1997)   (Correct)
Augmenting genetic algorithms with local search heuristics is a promising approach to the solution of combinatorial optimization problems. In this paper, a genetic local search approach to the quadrat... / the solution of combinatorial optimization problems. In this paper a br Compared to other combinatorial optimization problems such as the traveling

11   Constructive Feedforward Neural Networks for Regression Problems: A.. - Kwok, Yeung (1995)   (Correct)
In this paper, we review the procedures for constructing feedforward neural networks in regression problems. While standard back-propagation performs gradient descent only in the weight space of a net... / two general approaches to this optimization problem. One involves using a br can be performed using various optimization algorithms which will be

11   Path Planning Using Lazy PRM - Bohlin, Kavraki (2000)   (Correct)
This paper describes a new approach to probabilistic roadmap planners (PRMs). The overall theme of the algorithm, called Lazy PRM, is to minimize the number of collision checks performed during planni... / paths as follows. Genetic optimization is used to search for a br and random walks to escape local minima. Another interesting approach is

11   Coupled Geodesic Active Regions for Image Segmentation: A Level Set.. - Paragios, Deriche (1999)   (Correct)
This paper presents a novel variational method for image segmentation that unifies boundary and region-based information sources under the Geodesic Active Region framework. A statistical analysis ... / hA and hB Then the optimization procedure refers to a frame br modules and connects the optimization procedure with the the curve

11   A Semismooth Equation Approach To The Solution Of Nonlinear.. - De Luca, Facchinei, Kanzow (1995)   (Correct)
In this paper we present a new algorithm for the solution of nonlinear complementarity problems. The algorithm is based on a semismooth equation reformulation of the complementarity problem. We expl... / shown to be relevant to optimization algorithms. Recently the br D.P. Bertsekas Constrained Optimization and Lagrange Multiplier

10   A General Framework for Vertex Orderings, With Applications to.. - Alpert And (1996)   (Correct)
Vertex orderings have been successfully applied to problems in netlist clustering, for system partitioning and layout [2] [20]. We present a vertex ordering construction that encompasses most reasonab... / for comparison rather than optimization of clustering solutions. br and Lengauer that good local minima in the flattened instance are

10   Top-Down, Constraint-Driven Design Methodology Based Generation of a.. - Chang, Felt, Sangiovanni-Vincentelli (1992)   (Correct)
To accelerate the design cycle for analog circuits and mixed-signal systems, we have proposed a top-down, constraint-driven design methodology [1]. In this paper we present a complete design flow to i... / as behavioral level simulators optimization tools and physical layout br terminal locations etc. Optimization Minimize area Table

10   Blind Separation of Convolutive Mixtures and an Application in.. - Ehlers, Schuster (1997)   (Correct)
In this paper we propose a two-step-algorithm for the blind separation of convolutive mixtures. We show that its application to automatic speech recognition in a noisy environment yields good results.... / proposed in - because optimization procedures of this kind are br . Gunter Dueck New Optimization Heuristics Journal of

10   Solving Problems with Hard and Soft Constraints Using a Stochastic.. - Jiang (1995)   (Correct)
Stochastic local search is an effective technique for solving certain classes of large, hard propositional satisfiability problems, including propositional encodings of problems such as circuit synthe... / possible MAX-SAT encodings of an optimization problem are equally good. For br Thus we turned a method for optimization problems into one for decision

10   A potential reduction approach to the frequency assignment problem - Warners, Terlaky, Roos, Jansen (1995)   (Correct)
The frequency assignment problem is the problem of assigning frequencies to transmission links such that either no interference occurs, or the amount of interference is minimized. We present an algori... / approach to combinatorial optimization problems. We develop a br programming combinatorial optimization frequency assignment.

10   Fast Hierarchical Clustering and Other Applications of Dynamic.. - Eppstein (1998)   (Correct)
We develop data structures for dynamic closest pair problems with arbitrary (not necessarily geometric) distance functions, based on a technique previously used by the author for Euclidean closest pai... / basis computation and local optimization methods. Although dynamic br cluster centroid. . Local Optimization. Local search procedures such

10   Reevaluating Genetic Algorithm Performance under Coordinate Rotation.. - Salomon (1995)   (Correct)
This work analyzes some concepts of genetic algorithms and explains why they may be applied with success to some problems in function optimization. In addition to other performance properties, it has ... / to some problems in function optimization. In addition to other br cause a failure of the optimization procedure even though the

10   A Smoothing Method For Mathematical Programs With Equilibrium.. - Facchinei, Jiang, Qi (1996)   (Correct)
The mathematical program with equilibrium constraints (MPEC) is an optimization problem with variational inequality constraints. MPEC problems include bilevel programming problems as a particular ca... / constraints MPEC is an optimization problem with variational br equivalent one-level nonsmooth optimization problem. Then a sequence of

10   Activity Analysis: The Qualitative Analysis of Stationary Points for.. - Williams (1994)   (Correct)
We present a theory of a modeler's problem decomposition skills in the context of optimal reasoning --- the use of qualitative modeling to strategically guide numerical explorations of objective space... / and non-linear constrained optimization problems and easily br approaches of continuous optimization -combined with the

9   Improving Convergence and Solution Quality of Hopfield-Type Neural.. - Li (1996)   (Correct)
Hopfield-type networks convert a combinatorial optimization to a constrained real optimization and solve the latter using the penalty method. There is a dilemma with such networks: When tuned to produ... / networks convert a combinatorial optimization to a constrained real br to a constrained real optimization and solve the latter using the

9   Using Prediction to Improve Combinatorial Optimization Search - Boyan, Moore (1997)   (Correct)
To appear in AISTATS-97 This paper describes a statistical approach to improving the performance of stochastic search algorithms for optimization. Given a search algorithm A, we learn to predict the o... / to Improve Combinatorial Optimization Search Justin A. Boyan and br stochastic search algorithms for optimization. Given a search algorithm A

9   Evolution in a Rugged Fitness Landscape - Flyvbjerg, Lautrup (1992)   (Correct)
Kauffman's NK-model for genetic evolution and adaption is analysed for K = N \Gamma 1. In this case it describes adaptive walks on random fitness landscapes, and its dynamics is equivalent to the Met... / they crop up in combinatorial optimization problems and in the training br evolution to attack these hard optimization problems In the present

9   Learning without Local Minima in Radial Basis Function Networks - Bianchini, Frasconi, Gori (1995)   (Correct)
Learning from examples plays a central role in artificial neural networks (ANN). However, the success of many learning schemes is not guaranteed, since algorithms like Backpropagation (BP) may get stu... / essentially deal with the optimization of functions that in pattern br The rich literature on optimization algorithms still has to be

9   A Parallel Simulated Annealing Algorithm for Generating 3D Layouts of .. - Monien, Ramme, Salmen (1996)   (Correct)
In this paper, we introduce a parallel simulated annealing algorithm for generating aesthetically pleasing straight-line drawings. The proposed algorithm calculates high quality 3D layouts of arbitr... / annealing SA is a flexible optimization method suited for large-scale br for large-scale combinatorial optimization problems DLS JAMS -

9   Approximating Maximum Clique with a Hopfield Network - Jagota (1995)   (Correct)
In a graph, a clique is a set of vertices such that every pair is connected by an edge. MAX-CLIQUE is the optimization problem of finding the largest clique in a given graph, and is NP-hard, even to a... / by an edge. MAX-CLIQUE is the optimization problem of finding the largest br d c b a MAX-CLIQUE is the optimization problem of finding a largest

9   On Correlated Mutations in Evolution Strategies - Rudolph (1992)   (Correct)
this paper we are interested mainly in convergence speed of ESs such that we shall assume for simplicity that f has only one local minimum which is of course the global one. First work on this topic h... / been developed for experimental optimization i.e. optimization at the real br experimental optimization i.e. optimization at the real object. Later they

9   A grid algorithm for bound constrained optimization of noisy functions - Elster, Neumaier (1995)   (Correct)
The optimization of noisy functions is a common problem occurring in various applications. In this paper, a new approach is presented for low-dimensional bound constrained problems, based on the use... / algorithm for bound constrained optimization of noisy functions Clemens br ABSTRACT The optimization of noisy functions is a common

9   A Hardware Genetic Algorithm for the Traveling Salesman Problem on.. - Graham (1995)   (Correct)
With the introduction of Splash, Splash 2, PAM, and other reconfigurable computers, a wide variety of algorithms can now be feasibly constructed in hardware. In this paper, we describe the Splash 2 ... / Holland developed an optimization technique based on the process br has shown its usefulness for optimization problems requiring the search

9   Criticality and Parallelism in Combinatorial Optimization - Macready, Siapas, Kauffman (1995)   (Correct)
Local search methods constitute one of the most successful approaches to solving large-scale combinatorial optimization problems. A new result concerning the parallelization of such methods is present... / Parallelism in Combinatorial Optimization William G. Macready br large-scale combinatorial optimization problems. A new result

9   A Critique of Structure-from-Motion Algorithms - Oliensis (2000)   (Correct)
I critique current approaches to structure from motion and describe a new framework for algorithms. Keywords Structure from motion, multi--frame structure from motion, projective methods, invariants,... / Kalman filtering optimization trilinear reconstruction br approaches to SFM including optimization Kalman filtering and fusing

9   Nested Loop Sequences: Towards Efficient Loop Structures in Automatic .. - Chamski (1993)   (Correct)
An important problem in automatic parallelization of scientific programs is to generate loops from an algebraic description of the iteration domain. The usual technique is to produce a perfectly nes... / linear programming optimization. R'esum'e tsvp Unit e br programmation lin'eaire optimisation. Nested Loop Sequences

9   Flow Visualization for Turbomachinery Design - Roth, Peikert (1996)   (Correct)
Visualization of CFD data for turbomachinery design poses some special requirements which are often not addressed by standard flow visualization systems. We discuss the issues involved with this parti... / CFD is routinely used for optimization and comparison To br helicity with apparent vortices. Minima of pressure A technique which

9   Glopeq: A New Computational Tool For The Phase And Chemical.. - M.Mcdonald (1997)   (Correct)
Calculation of phase and chemical equilibrium represents a crucial phase in the modeling of many separation processes. For conditions of constant temperature and pressure, a necessary and sufficient... / models GLOPEQ Global OPtimization for the Phase and chemical br phases. However the local optimization approaches which are in common

9   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... / is converted into a nonlinear optimization problem with the match matrix br via and and subsequent optimization w.r.t. them is referred to as

9   Global Optimization For The Phase And Chemical Equilibrium Problem.. - Mcdonald (1994)   (Correct)
Several approaches have been proposed for the computation of solutions to the phase and chemical equilibrium problem when the problem is posed as the minimization of the Gibbs free energy function. No... / Global Optimization For The Phase And Chemical br Secondly the Global OPtimization GOP algorithm Floudas and

9   An Analytical Constant Modulus Algorithm - van der Veen, Paulraj (1996)   (Correct)
Iterative constant modulus algorithms such as Godard and CMA have been used to blindly separate a superposition of co-channel constant modulus (CM) signals impinging on an antenna array. These algorit... / of the gradient descent optimization the CMAs do converge sometimes br Additive Noise A. Equivalent Optimization Problem With Noise Added To

9   Optimal Structure From Motion: Local Ambiguities and Global Estimates - Soatto (1998)   (Correct)
We present an analysis of SFM from the point of view of noise. This analysis results in an algorithm that is provably convergent and provably optimal with respect to a chosen norm. In particular, we c... / we cast SFM as a nonlinear optimization problem and define a bilinear br generalpurpose nonlinear optimization techniques on cost functions

8   Unsupervised Learning by Convex and Conic Coding - Lee, Seung (1997)   (Correct)
Unsupervised learning algorithms based on convex and conic encoders are proposed. The encoders find the closest convex or conic combination of basis vectors to the input. The learning algorithms produ... / of as a heavily constrained optimization of Eq. a single v a br with this constraint the optimization of Eq. becomes an integer

8   GSAT versus Simulated Annealing - Beringer, Aschemann, Hoos, Weiß (1994)   (Correct)
The question of satisfiability for a given propositional formula arises in many areas of AI. Especially finding a model for a satisfiable formula is very important though known to be NP-complete. Th... / which is often used for optimization and constraint satisfaction br C.D. Gelatt and M.P. Vecchi Optimization by simulated annealing'

8   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... / done for discrete constrained optimisation problems br In systems for constrained optimization problems with continous

8   Second-Order Stability Cells of a Frictionless Rigid Body Grasped by.. - Trinkle, Farahat, Stiller (1994)   (Correct)
The most secure type of grasp of a frictionless woorkpiece is the form-closure grasp. However, task constraints may make achieving form-closure impossible or undesirable. In this case, one needs to em... / of the following nonlinear optimization problem Minimize q br and M. H. Wright. Practical Optimization. Academic Press . H.

8   A Statistical Mechanical Formulation of the Dynamics of Genetic.. - Shapiro, Prügel-Bennett, Rattray (1994)   (Correct)
A statistical mechanical formulation of the dyamics of genetic algorithms is described. This formulation allows the derivation of equations which predict the distributions of fitness with the popula... / theory neural networks and optimization for examples see As an br one and two dimensional function optimization problems. We consider the

8   Global Optimization And Analysis For The Gibbs Free Energy Function.. - McDonald, Floudas (1994)   (Correct)
The Wilson equation for the excess Gibbs energy has found wide use in successfully representing the behavior of polar and nonpolar multicomponent mixtures with only binary parameters, but was incapabl... / Global Optimization And Analysis For The Gibbs br is provided so that a local optimization technique will always converge

8   A novel optimizing network architecture with applications - Rangarajan, Gold, al. (1996)   (Correct)
We present a novel optimizing network architecture with applications in vision, learning, pattern recognition and combinatorial optimization. This architecture is constructed by combining the followin... / recognition and combinatorial optimization. This architecture is br to many hard combinatorial optimization problems. The results for

8   A Multi-frame Structure-from-Motion Algorithm under Perspective.. - Oliensis (1997)   (Correct)
We present a fast, robust algorithm for multi--frame structure from motion from point features which works for general motion and large perspective effects. Experimental results on synthetic and real ... / the MATLAB implementation of optimization via Levenberg-Marquardt br We have tried several MATLAB optimization routines without obtaining

8   An Updated Survey of Evolutionary Multiobjective Optimization.. - Coello (1999)   (Correct)
This paper reviews some of the most popular evolutionary multiobjective optimization techniques currently reported in the literature, indicating some of their main applications, their advantages, disa... / of Evolutionary Multiobjective Optimization Techniques State of the Art br evolutionary multiobjective optimization techniques currently reported

8   Combinatorial Optimization by Iterative Partial Transcription - Möbius, Freisleben, Merz, Schreiber (1999)   (Correct)
A procedure is presented which considerably improves the performance of local search based heuristic algorithms for combinatorial optimization problems. It increases the average "gain" of the individu... / Feb Combinatorial Optimization by Iterative Partial br algorithms for combinatorial optimization problems. It increases the

8   A Stochastic Approach to the Weighted-Region Problem: Design and.. - Kindl, Shing, Rowe (1991)   (Correct)
This paper presents an efficient heuristic algorithm for planning near-optimal high-level paths for a point agent moving through complex terrain modeled by the Weighted-Region Problem. The input to th... / search with probabilistic optimization by simulated annealing. It br it solves a convex local-optimization subproblem to find the

8   Effective Multifingered Grasp Synthesis - Jefferson Coelho Jr (1994)   (Correct)
This report discusses the issues involved in developing a grasp controller, within the framework of control composition, and introduces control pre-imaging. Pre-imaging is a design technique for aug... / synthesis optimization-based grasp synthesis br solution contact geometry is an optimization based on shape rather than

8   Bayesian Inference on Visual Grammars by Neural Nets that Optimize - Mjolsness (1990)   (Correct)
We exhibit a systematic way to derive neural nets for vision problems. It involves formulating a vision problem as Bayesian inference or decision on a comprehensive model of the visual domain given by... / distribution in terms of the optimization of an objective function E. br may be approximated by an optimization over near-permutations as we

8   A Family of Variable Metric Proximal Methods - Bonnans, Gilbert, Lemaréchal.. (1995)   (Correct)
We consider conceptual optimization methods combining two ideas: the MoreauYosida regularization in convex analysis, and quasi-Newton approximations of smooth functions. We outline several approache... / We consider conceptual optimization methods combining two ideas br Bundle methods convex optimization global and superlinear

8   On-line learning processes in artificial neural networks - Heskes, Kappen (1993)   (Correct)
We study on-line learning processes in artificial neural networks from a general point of view. On-line learning means that a learning step takes place at each presentation of a randomly drawn trainin... / of on-line learning for global optimization. In J. Taylor editor br might be used as a global optimization method. We derive cooling

8   An Iterative Improvement Algorithm for Low Power Data Path Synthesis - Raghunathan (1995)   (Correct)
We address the problem of minimizing power consumption in behavioral synthesis of data-dominated circuits. The complex nature of power as a cost function implies that the effects of several behavioral... / methods of behavioral power optimization like data path replication and br work in architectural power optimization was presented in which

8   Molecular Modeling Of Proteins And Mathematical Prediction Of Protein .. - Neumaier (1997)   (Correct)
This paper discusses the mathematical formulation of and solution attempts for the so-called protein folding problem. The static aspect is concerned with how to predict the folded (native, tertiary)... / data and the global optimization of the potential. The dynamic br conformational entropy global optimization simulated annealing genetic

8   A New Scheme for Incremental Learning - Jutten, Chentouf (1995)   (Correct)
We present a new incremental procedure for supervised learning with noisy data. Each step consists in adding to the current network a new unit which is trained to learn the error of the network. The i... / ffl k x Because the optimization of the k-network and of the new br after a Least Square LS optimization is the realization of a

8   Using 3-Dimensional Meshes To Combine Image-Based and Geometry-Based.. - Fua, Leclerc (1994)   (Correct)
A unified framework for 3--D shape reconstruction allows us to combine image-based and geometry-based information sources. The image information is akin to stereo and shape-fromshading, while the geom... / our weighting scheme and our optimization method. Finally we present br in an iterative manner using an optimization algorithm. Recent publications

8   Parallel Implementation of Algorithms for Finding Connected.. - Hsu, Ramachandran, Dean (1997)   (Correct)
In this paper, we describe our implementation of several parallel graph algorithms for finding connected components. Our implementation, with virtual processing, is on a 16,384-processor MasPar MP-1... / Parallel processing of discrete optimization problems DIMACS series in br in trees and range minima More complex

8   An Intelligent, Predictive Control Approach to the High-Speed.. - Kelly (1995)   (Correct)
Autonomous robot vehicles promise many ultimate civilian, military, and space applications. Off-road autonomous vehicles must engage the world exactly as they find it without relying on having it engi... / achieved through a quantitative optimization process. The reliability of br before obstacle avoidance. In optimization terms such a system considers

8   Cooperative - Competitive Genetic Evolution of Radial Basis Function.. - Whitehead, Choate (1995)   (Correct)
In a radial basis function (RBF) network, the RBF centers and widths can be evolved by a cooperativecompetitive genetic algorithm. The set of genetic strings in one generation of the algorithm represe... / approaches to neural network optimization have emphasized purely br various approaches to genetic optimization of neural networks fitting

7   Learning with preknowledge: clustering with point and graph matching.. - Gold, Rangarajan, al. (1996)   (Correct)
Prior knowledge constraints are imposed upon a learning problem in the form of distance measures. Prototypical 2-D point sets and graphs are learned by clustering with point matching and graph matchin... / Learning is formulated as an optimization problem. Large objectives so br minimized using a combination of optimization techniques-softassign

7   Speeding up Variable Reordering of OBDDs - Meinel, Slobodova (1997)   (Correct)
In this paper, we suggest a block-restricted sifting strategy which is based on the restriction of Rudell's sifting to certain blocks of variables. The application of this strategy results in a consid... / sizes. The main resource for the optimization of the OBDD size is the choice br result in an essential loss in optimization while time could be decreased

7   Dynamic Hill Climbing: Overcoming the limitations of optimization.. - Yuret, Maza (1993)   (Correct)
This paper describes a novel search algorithm, called dynamic hill climbing, that borrows ideas from genetic algorithms and hill climbing techniques. Unlike both genetic and hill climbing algorithms, ... / Overcoming the limitations of optimization techniques Deniz Yuret and br frame during the course of an optimization. Furthermore the algorithm

7   Combining Problem Reduction and Adaptive Multi-Start: A New Technique .. - Hagen (1995)   (Correct)
VLSI netlist partitioning has been addressed chiefly by iterative methods (e.g. KernighanLin [21] and Fiduccia-Mattheyses [13]) and spectral methods (e.g. Hagen-Kahng [14]). Iterative methods are the ... / points for the iterative optimization based on the results of br based on the results of previous optimizations. The resulting Clustered

7   Efficient Massively Parallel Implementation of Some Combinatorial.. - Hsu, Ramachandran (1996)   (Correct)
We describe our implementation of several efficient parallel algorithms on the massively parallel SIMD machine MasPar MP-1 with virtual processing. The MPL language that we used on the MasPar MP-1 doe... / of parallel primitives and optimization techniques used and presents br Parallel processing of discrete optimization problems volume of DIMACS

7   An Automatic Method Of Finding Topic Boundaries - Reynar (1994)   (Correct)
This article outlines a new method of locating discourse boundaries based on lexical cohesion and a graphical technique called dotplotting. The application of dotplotting to discourse segmentation can... / or automatically using an optimization algorithm. The results of two br correspond to the most extreme minima-those at positions

7   The Exit Path Of A Markov Chain With Rare Transitions - Catoni, Cerf (1995)   (Correct)
We study the exit path from a general domain after the last visit to a set of a Markov chain with rare transitions. We prove several large deviation principles for the law of the succession of the c... / from statistical mechanics to optimization and reliability theory. This br state to a stable one. For an optimization algorithm it is described as

7   Self-Organizing Maps: Generalizations and New Optimization Techniques - Graepel, Burger, Obermayer (1998)   (Correct)
We offer three algorithms for the generation of topographic mappings to the practitioner of unsupervised data analysis. The algorithms are each based on the minimization of a cost function which is pe... / Maps Generalizations and New Optimization Techniques Thore Graepel br maps of Euclidean data. Its optimization scheme however offers an

7   Automated Decomposition of Model-based Learning Problems - Brian Williams (1996)   (Correct)
A new generation of sensor rich, massively distributed autonomous systems is being developed that has the potential for unprecedented performance, such as smart buildings, reconfigurable factories, ad... / a -dimensional nonlinear optimization problem involving a br the concept of a conflict a minimal subset of a model typically in

7   Complexity Classes of Optimization Functions - Vollmer, Wagner (1995)   (Correct)
In this paper, complexity classes of functions defined via taking maxima or minima (cf. the work of Krentel) or taking middle elements (cf. the work of Toda) are examined. A number of axioms for a cla... / Complexity Classes of Optimization Functions Heribert br a so called p-founded class of optimization functions are given. It is

7   Text Categorization Using Weight Adjusted k-Nearest Neighbor.. - Han, Karypis, Kumar (1999)   (Correct)
Text categorization is the task of deciding whether a document belongs to a set of prespecified classes of documents. Automatic classification schemes can greatly facilitate the process of categorizat... / weight using conjugate gradient optimization She Unlike PEBLS VSM br each iteration according to an optimization function. This algorithm is

7   Globally Optimal Regions and Boundaries - Jermyn, Ishikawa (1999)   (Correct)
We propose a new form of energy functional for the segmentation of regions in images, and an efficient method for finding its global optima. The energy can have contributions from both the region and ... / footing and solve the global optimization problem as a minimum mean br the region. The solution to the optimization problem is the global maximum

7   Approximation algorithms for MAX 4-SAT and rounding procedures for.. - Halperin, Zwick (1999)   (Correct)
Karloff and Zwick obtained recently an optimal 7=8-approximation algorithm for MAX 3-SAT. In an attempt to see whether similar methods can be used to obtain a 7=8-approximation algorithm for MAX ... / SAT is one of the most natural optimization problems. An instance of MAX br goal. The fact that numerical optimization techniques were used to compute

7   Genetic Algorithms for Gait Synthesis in a Hexapod Robot - Lewis, Fagg, Bekey (1994)   (Correct)
This paper describes the staged evolution of a complex motor pattern generator (CPG) for the control of the leg movements of a six-legged walking robot. The CPG is composed of a network of neurons. ... / gaits of animals and proposed optimization criteria for gaits and compares br such a function displays multiple minima in the parameter space and most

7   Error Bounds for Analytic Systems and Their Applications - Luo (1994)   (Correct)
Using a 1958 result of Lojasiewicz, we establish an error bound for analytic systems consisting of equalities and inequalities defined by real analytic functions. In particular, we show that over any ... / in SIAM Journal on Control and Optimization. O. Guler A.J. Hoffman br SIAM Journal on Control and Optimization - .

7   Neural Networks and Complexity Theory - Orponen (1992)   (Correct)
We survey some of the central results in the complexity theory of discrete neural networks, with pointers to the literature. 1 Introduction The recently revived field of computation by "neural" n... / and solving combinatorial optimization problems. Numerous algorithms br in finding the absolutely minimal circuit responding correctly to a

7   Proper Orthogonal Decomposition for Flow Calculations and Optimal.. - Ly, Tran (1998)   (Correct)
Proper orthogonal decomposition (which is also known as the Karhunen Lo`eve decomposition) is a reduction method that is used to obtain low dimensional dynamic models of distributed parameter system... / In Ito et al. a shape optimization problem with respect to the br conditions and a numerical optimization method based on the augmented

7   The Racing Algorithm: Model Selection for Lazy Learners - Maron, Moore (1997)   (Correct)
Given a set of models and some training data, we would like to find the model that best describes the data. Finding the model with the lowest generalization error is a computationally expensive proces... / the number of models is large. Optimization techniques such as hill br Genetic Algorithms in Search Optimization and Machine Learning.

6   Memetic Algorithms and the Fitness Landscape of the Graph.. - Merz, Freisleben (1998)   (Correct)
In this paper, two types of fitness landscapes of the graph bipartitioning problem are analyzed, and a memetic algorithm -- a genetic algorithm incorporating local search -- that finds near-optimum ... / is an NP-hard combinatorial optimization problem that arises in br b general-purpose heuristic optimization approaches such as simulated

6   The Average Case Analysis Of Algorithms - Saddle Point Asymptotics - Flajolet, Sedgewick (1994)   (Correct)
This report is part of a series whose aim is to present in a synthetic way the major methods of "analytic combinatorics" needed in the average--case analysis of algorithms. The series should comprise ... / shortly. Notice that the optimization problem need not be solved br are useful in combinatorial optimization the knapsack problem and

6   On Training Neural Nets through Stochastic Minimization - Brunelli (1994)   (Correct)
The revival of multilayer neural networks in the mid 80's originated from the discovery of the backpropagation technique as a feasible training procedure. In spite of its shortcomings, it is probably ... / Keywords stochastic optimization learning algorithms br represent two alternative optimization techniques based on random

6   Multidimensional Scaling and Data Clustering - Hofmann, Buhmann (1995)   (Correct)
Visualizing and structuring pairwise dissimilarity data are difficult combinatorial optimization problems known as multidimensional scaling or pairwise data clustering. Algorithms for embedding dissi... / data are difficult combinatorial optimization problems known as br Euclidian space is a non-convex optimization problem which typically

6   Novel On-line Adaptive Learning Algorithms for Blind Deconvolution.. - Amari, Douglas, Cichocki, Yang (1997)   (Correct)
Blind deconvolution is an important task for numerous applications in control, signal processing, and communications. In this paper, the efficient natural gradient [Amari et.al. (1996)] or relative ... / that stochastic gradient optimization methods for parameterized br function OE W z k whose minima provide proper deconvolution of

6   Lagrangian Techniques for Solving a Class of Zero-One Integer Linear.. - Chang (1995)   (Correct)
We consider a class of zero-one integer programming feasibility problems (0-1 ILPF problems) in which the coefficients of variables can be integers, and the objective is to find an assignment of binar... / into an unconstrained global optimization problem in real space. Using a br methods for solving constrained optimization problems. Little work has been

6   How good are genetic algorithms at finding large cliques: an.. - Carter (1993)   (Correct)
This paper investigates the power of genetic algorithms at solving the MAX-CLIQUE problem. We measure the performance of a standard genetic algorithm on an elementary set of problem instances consisti... / Challenge on Combinatorial Optimization DIMACS October . y br are general-purpose optimization methods that have gained wide

6   Recognizing Emotion In Speech - Dellaert, Polzin, Waibel (1996)   (Correct)
This paper explores several statistical pattern recognition techniques to classify utterances according to their emotional content. We have recorded a corpus containing emotional speech with over a 10... / Set B. . Distance Metric Optimization In This And The Following br is quite rugged so classical optimization techniques like gradient

6   Guided Local Search - Voudouris, Tsang (1995)   (Correct)
Guided Local Search (GLS) is an intelligent search scheme for combinatorial optimization problems. A main feature of the approach is the iterative use of local search. Information is gathered from var... / search scheme for combinatorial optimization problems. A main feature of br with well-known and established optimization techniques such as simulated

6   Multidimensional Scaling by Deterministic Annealing - Klock, Buhmann (1997)   (Correct)
Multidimensional scaling addresses the problem how proximity data can be faithfully visualized as points in a low-dimensional Euclidian space. The quality of a data embedding is measured by a cost f... / coordinates for this continuous optimization problem. Experimental results br the superiority of the optimization technique compared to

6   A Global Optimization Approach for Lennard-Jones Microclusters - Maranas, Floudas (1992)   (Correct)
A global optimization approach is proposed for finding the global minimum energy configuration of Lennard--Jones microclusters. First, the original nonconvex total potential energy function, composed ... / A Global Optimization Approach for Lennard-Jones br Abstract A global optimization approach is proposed for

6   A Study of the Mean Field Approach to Knapsack Problems - Ohlsson, Pi (1997)   (Correct)
The mean field theory (MFT) approach to knapsack problems is extended to multiple knapsacks and generalized assignment problems with Potts mean field equations governing the dynamics. Numerical test... / example of a combinatorial optimization problem with inequality br to difficult combinatorial optimization problems The

6   Guessing Can Outperform Many Long Time Lag Algorithms - Jürgen Schmidhuber, Sepp Hochreiter (1996)   (Correct)
Numerous recent papers focus on standard recurrent nets' problems with long time lags between relevant signals. Some propose rather sophisticated, alternative methods. We show: many problems used to t... / time-weighted pseudo-Newton optimization and discrete error br n and A Flat minima. It should be mentioned that

6   SDO: A Statistical Method for Global Optimization - Cox, John (1997)   (Correct)
An algorithm for finding global optima using statistical prediction is presented. Assuming a random function model, lower confidence bounds on predicted values are used for sequential selection of eva... / A Statistical Method for Global Optimization Dennis D. Cox y br in the problem of global optimization of nonlinear functions since

6   Parallel Approaches to Stochastic Global Optimization - Rudolph (1992)   (Correct)
In this paper we review parallel implementations of some stochastic global optimization methods on MIMD computers. Moreover, we present a new parallel version of an Evolutionary Algorithm for global o... / Approaches to Stochastic Global Optimization Gunter Rudolph br of some stochastic global optimization methods on MIMD computers.

6   Handling Inequality Constraints In Continuous Nonlinear Global.. - Tao Wang (1996)   (Correct)
In this paper, we present a new method to handle inequality constraints and apply it in NOVEL (Nonlinear Optimization via External Lead), a system we have developed for solving constrained continuous ... / In Continuous Nonlinear Global Optimization Tao Wang And Benjamin W. br apply it in NOVEL Nonlinear Optimization via External Lead a system we

6   The Theory of Discrete Lagrange Multipliers for Nonlinear Discrete.. - Wah, Wu (1999)   (Correct)
In this paper we present a Lagrange-multiplier formulation of discrete constrained optimization problems, the associated discrete-space first-order necessary and sufficient conditions for saddle poi... / for Nonlinear Discrete Optimization Benjamin W. Wah and Zhe br of discrete constrained optimization problems the associated

CiteSeer - citeseer.org - Terms of Service - Privacy Policy - Copyright © 1997-2002 NEC Research Institute