Adaptive Processing of Sequences and Data Structures: International Summer School on Neural Networks, "E.R. Caianiello", Vietri Sul Mare, Salerno, Italy, September 6-13, 1997, Tutorial Lectures
This book is devoted to adaptive processing of structured information similar to flexible and intelligent information processing by humans - in contrast to merely sequential processing of predominantly symbolic information within a deterministic framework. Adaptive information processing allows for a mixture of sequential and parallel processing of symbolic as well as subsymbolic information within deterministic and probabilistic frameworks.
The book originates from a summer school held in September 1997 and thus is ideally suited for advanced courses on adaptive information processing and advanced learning techniques or for self-instruction. Research and design professionals active in the area of neural information processing will find it a valuable state-of-the-art survey.
Gradient Based Learning Methods
Diagrammatic Methods for Deriving and Relating Temporal Neural Network Algorithms
An Introduction to Learning Structured Information
Neural Networks for Processing Data Structures
Topics in Complexity
Learning Dynamic Bayesian Networks
Probabilistic Models of Neuronal Spike Trains
Temporal Models in Blind Source Separation
Recursive Neural Networks and Automata
Architecture Dynamics and Training
Neural Dynamics with Stochasticity
The Value of EventBased Segmentation in a Complex RealWorld Control Problem
Overview and New Research Directions
Predictive Models for Sequence Modelling Application to Speech and Character Recognition
Other editions - View all
Adaptive Processing of Sequences and Data Structures: International Summer ...
C.Lee Giles,Marco Gori
No preview available - 2003
adjoint network approach approximation assume automata automaton backpropagation Bayesian network binary complexity consider corresponding data structures defined denote density derivatives deterministic discrete DOAG dynamic encoding equations error function estimate event-based segmentation example extraction FCHLRNN feedback feedforward filter finite finite state automata finite-state Gaussian given gradient descent grammar grammatical inference hidden layer neurons hidden Markov models IEEE implemented independent input string input symbol labeled learning algorithms length likelihood linear Markov models matrix methods minimal multilayer perceptrons network architecture Neural Computation neurons NNPDA node nonlinear optimal P/poly parameters perceptron posterior probability probabilistic probabilistic Turing machine probability quantization recurrent networks recurrent neural networks representation represented RNN architecture sequence shown signal space speech recognition spike stack reading statistical independence step stochastic networks supersource synapses temporal Theorem tion training set transduction transposed update values variables vector weights