Table of Contents



Architectures and Learning in Recurrent Neural Networks

Recurrent Neural Network Architectures: An Overview . . . . . . . . . . . . . . . . .                                     1
   A.C. Tsoi

Gradient Based Learning Methods . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 27
   A.C. Tsoi

Diagrammatic Methods for Deriving and Relating Temporal Neural
Network Algorithms . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 63
   E.A. Wan and F. Beaufays

Processing of Data Structures

An Introduction to Learning Structured Information . . . . . . . . . . . . . . . . . . . 99
   P. Frasconi

Neural Networks for Processing Data Structures . . . . . . . . . . . . . . . . . . . . . . . 121
   A. Sperduti

The Loading Problem: Topics in Complexity . . . . . . . . . . . . . . . . . . . . . . . . . . 145
  M. Gori

Probabilistic Models

Learning Dynamic Bayesian Networks . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 168
   Z. Ghahramani

Probabilistic Models of Neuronal Spike Trains . . . . . . . . . . . . . . . . . . . . . . . . . 198
   P. Baldi

Temporal Models in Blind Source Separation . . . . . . . . . . . . . . . . . . . . . . . . . . 229
   L.C. Parra

Analog vs Symbolic Computation

Recursive Neural Networks and Automata . . . . . . . . . . . . . . . . . . . . . . . . . . . . 248
   M. Maggini

The Neural Network Pushdown Automaton: Architecture, Dynamics
and Training . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 296
   G.Z. Sun, C.L. Giles and H.H. Chen

Neural Dynamics with Stochasticity . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 346
   H. T. Siegelmann
XII        Table of Contents

Applications

Parsing the Stream of Time: The Value of Event-Based Segmentation
in a Complex Real-World Control Problem . . . . . . . . . . . . . . . . . . . . . . . . . . . . 370
    M.C.Mozer and D. Miller
Hybrid HMM/ANN Systems for Speech Recognition: Overview and
New Research Directions . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 389
  H. Bourlard and N. Morgan

Predictive Models for Sequence Modelling, Application to Speech and
Character Recognition . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 418
   P. Gallinari