by Peter Whittle (University of Cambridge, UK)

Table of Contents (99k)
Preface (90k)
Chapter 1: Introduction and Aspirations (126k)

Neural Nets and Chaotic Carriers develops rational principles for the design of associative memories, with a view to applying these principles to models with irregularly oscillatory operation so evident in biological neural systems, and necessitated by the meaninglessness of absolute signal levels.

Design is based on the criterion that an associative memory must be able to cope with “fading data”, i.e., to form an inference from the data even as its memory of that data degrades. The resultant net shows striking biological parallels. When these principles are combined with the Freeman specification of a neural oscillator, some remarkable effects emerge. For example, the commonly-observed phenomenon of neuronal bursting appears, with gamma-range oscillation modulated by a low-frequency square-wave oscillation (the “escapement oscillation”). Bridging studies and new results of artificial and biological neural networks, the book has a strong research character. It is, on the other hand, accessible to non-specialists for its concise exposition on the basics.

• Opening and Themes:
  • Introduction and Aspirations
  • Optimal Statistical Procedures
  • Linear Links and Nonlinear Knots: The Basic Neural Net
  • Bifurcations and Chaos
• Associative and Storage Memories:
  • What is a Memory? The Hamming and Hopfield Nets
  • Compound and ‘Spurious’ Traces
  • Preserving Plasticity: A Bayesian Approach
  • The Key Task: The Fixing of Fading Data. Conclusions I
  • Performance of the Probability-Maximising Algorithm
  • Other Memories — Other Considerations
• Oscillatory Operation and the Biological Model:
  • Neuron Models and Neural Masses
  • Freeman Oscillators — Solo and in Concert
  • Associative Memories Incorporating the Freeman Oscillator
  • Olfactory Comparisons. Conclusions II
  • Transmission Delays