(Enter summary)
Abstract: 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 measure. The algorithm does not make any assumpt
tions about transfer functions of individual neurons, and does not explicitly depend on
he functional form of the error measure. Hence, it can be used in networks with arbi-
-
i
trary transfer functions and for minimizing a large class of error... (Update)
Context of citations to this paper: More
...which contain many saddle points and at areas. Although this problem can be solved by using stochastic learning methods (e.g. [9,1,13]) these methods require many learning iterations in order to nd an optimum, and are therefore not suited for problems where fast...
...become very small and result in miniscule changes in weights at each iteration. Unnikrishnan and Venugopal present Alopex algorithm in [UV94] This algorithm does not assume anything about the error function used, and can train any ANN, irrespective of the squashing function,...
Cited by: More
Symplectic Nonlinear Component - Analysis Lucas Parra
(Correct)
Frequency-Based Error Back-Propagation in a Cortical Network - Rafal Bogacz Malcolm (2000)
(Correct)
Evolutionary Learning on Structured Data for Artificial Neural.. - Radlinski
(Correct)
Active bibliography (related documents): More All
0.3: Learning Situation-Specific Control In Multi-Agent Systems - Prasad (1997)
(Correct)
0.3: Connectionist Learning for Control: An Overview - Barto (1989)
(Correct)
0.1: Internal Reinforcement in a Connectionist Genetic Programming .. - Teller, Veloso
(Correct)
Similar documents based on text: More All
0.4: K P Venugopal - Computer Science Department
(Correct)
0.2: Robust Extraction of Multiple Structures from.. - Unnikrishnan, Hebert (2003)
(Correct)
0.2: Aligning Knowledge Management with - Customer Requirements In (2001)
(Correct)
Related documents from co-citation: More All
5: Pattern Recognition and Neural Networks
- Ripley - 1996
4: Learning Internal Representations by Error Propagation (context) - Rumelhart, Hinton et al. - 1986
4: Neural Networks for Pattern Recognition (context) - Bishop - 1995
BibTeX entry: (Update)
K. P. Unnikrishnan and K. P. Venugopal. Alopex: A correlation-based learning algorithm for feedforward and recurrent neural networks. Neural Computation, 6:469--490, 1994. http://citeseer.ist.psu.edu/unnikrishnan94alopex.html More
@article{ unnikrishnan94alopex,
author = "K. P. Unnikrishnan and K. P. Venugopal",
title = "Alopex: {A} Correlation-Based Learning Algorithm for Feedforward and Recurrent Neural Networks",
journal = "Neural Computation",
volume = "6",
number = "3",
pages = "469--490",
year = "1994",
url = "citeseer.ist.psu.edu/unnikrishnan94alopex.html" }
Citations (may not include all citations):
180
Connectionist learning procedures (context) - Hinton - 1989
28
Learning by statistical cooperation of self-interested neuro.. (context) - Barto - 1985
27
Supervised learning of probability distributions b eural net.. (context) - Baum - 1988
6
Learning internal represen ations by error propagation (context) - Rumelhart, Hinton et al. - 1986
3
Game-theoretic cooperativity in networks of self-interested .. (context) - Barto - 1986
1
A feedback model of visual attention (context) - technique, VLSI et al. - 1992
1
Model-free distributed learning (context) - mechanisms, Ann et al. - 1990
1
Dynamical control of attention throug eedback pathways: A ne.. (context) - Recognition, Network et al. - 1992
1
Perception as an optimization H process (context) - to, combustion et al. - 1986
1
Learning automata: an introduction (context) - functions, SMC et al. - 1989
1
Cortical feedback to LGN may play ajor role in ocular domina.. (context) - Unnikrishnan - 1991
1
Brainstem control of sensory information: a H mechanism for .. (context) - fields, Res et al. - 1985
1
The role of subplate feedback in th evelopment of ocular dom.. (context) - Nine - 1993
1
Learning in hierarchical neural networks U with feedback (context) - of, columns et al. - 1991
1
Associative search network: einforcement learning associativ.. (context) - Barto, Sutton et al. - 1981
1
Principles of neurodynamics (context) - algorithm, osenblatt - 1962
1
Multilayer feed-forward networks are J universal approximato.. (context) - feed-back, Proc et al. - 1989
1
Gradient following without back-propagation i ayered network.. (context) - Barto - 1987
1
the convergence properties of the Alo ex algorithm (context) - Sastry - 1993
1
Learning symmetry groups S with hidden units: beyond the per.. (context) - Sejnowski, Kienker et al. - 1986
1
A recurrent network con roller and learning algorithm for th.. (context) - Venugopal, Pandya et al.
1
Pioneer neurons and target selection in cerebral cortical T .. (context) - Shatz - 1990
1
An adaptive system for control of aircraft and spacecraft (context) - of, Kybernetik et al. - 1959
1
Carnegie Mellon University (context) - algorithms - 1991
The graph only includes citing articles where the year of publication is known.
Documents on the same site (ftp://ftp.cis.ohio-state.edu/pub/neuroprose/): More
Feedforward Hebbian Learning with Nonlinear Output Units: A.. - Troyer (1994)
(Correct)
Soft Classification, a. k. a. Risk Estimation, via.. - Wahba, Gu, Wang.. (1993)
(Correct)
Oscillatory Model of Short Term Memory - Horn, Usher (1992)
(Correct)
Online articles have much greater impact More about CiteSeer.IST Add search form to your site Submit documents Feedback
CiteSeer.IST - Copyright Penn State and NEC