Neural Computation

Volume 4 : Issue 2

Table of Contents

• First- and Second-Order Methods for Learning: Between Steepest Descent and Newton's Method 
  Roberto Battiti
  Page 141
• Efficient Simplex-Like Methods for Equilibria of Nonsymmetric Analog Networks 
  Douglas A. Miller and Steven W. Zucker
  Page 167
• A Volatility Measure for Annealing in Feedback Neural Networks 
  Joshua Alspector, Torsten Zeppenfeld and Stephan Luna
  Page 191
• What Does the Retina Know about Natural Scenes? 
  Joseph J. Atick and A. Norman Redlich
  Page 196
• A Simple Network Showing Burst Synchronization without Frequency Locking 
  Christof Koch and Heinz Schuster
  Page 211
• On a Magnitude Preserving Iterative MAXnet Algorithm 
  Bruce W. Suter and Matthew Kabrisky
  Page 224
• Learning Complex, Extended Sequences Using the Principle of History Compression 
  Jrgen Schmidhuber
  Page 234
• A Fixed Size Storage O(n³) Time Complexity Learning Algorithm for Fully Recurrent Continually Running Networks 
  Jrgen Schmidhuber
  Page 243
• How Tight Are the Vapnik-Chervonenkis Bounds? 
  David Cohn and Gerald Tesauro
  Page 249
• Working Memory Networks for Learning Temporal Order with Application to Three-Dimensional Visual Object Recognition 
  Gary Bradski, Gail A. Carpenter and Stephen Grossberg
  Page 270