CLSWeb Main
Caltech Library System
Electronic Theses
                  About | Browse | Search | Caltech Student Instructions

Atiya, Amir (1991-01-01) Learning algorithms for neural networks. http://resolver.caltech.edu/CaltechETD:etd-09232005-083502


Type of Document Dissertation
Author Atiya, Amir
Author's Email Address amir AT alumni.caltech.edu
URN etd-09232005-083502
Persistent URL http://resolver.caltech.edu/CaltechETD:etd-09232005-083502
Title Learning algorithms for neural networks
Degree PhD
Option Electrical Engineering
Advisory Committee
Advisor Name Title
Yaser S. Abu-Mostafa Committee Chair
Carver Mead Committee Member
Demetri Psaltis Committee Member
Edward Posner Committee Member
Keywords
  • recurrent neural networks
  • training algorithms
  • stability of neural networks
  • unsupervised learning
  • clustering
  • oscillations
  • oscillations of neural networks
  • convergence of neural networks
  • Hopfield model
  • backpropagation
Date of Defense 1991-01-01
Availability unrestricted
Abstract
This thesis deals mainly with the development of new learning algorithms and the study of the dynamics of neural networks. We develop a method for training feedback neural networks. Appropriate stability conditions are derived, and learning is performed by the gradient descent technique. We develop a new associative memory model using Hopfield's continuous feedback network. We demonstrate some of the storage limitations of the Hopfield network, and develop alternative architectures and an algorithm for designing the associative memory. We propose a new unsupervised learning method for neural networks. The method is based on applying repeatedly the gradient ascent technique on a defined criterion function. We study some of the dynamical aspects of Hopfield networks. New stability results are derived. Oscillations and synchronizations in several architectures are studied, and related to recent findings in biology. The problem of recording the outputs of real neural networks is considered. A new method for the detection and the recognition of the recorded neural signals is proposed.

Files
  Filename       Size       Approximate Download Time (Hours:Minutes:Seconds) 
 
 28.8 Modem   56K Modem   ISDN (64 Kb)   ISDN (128 Kb)   Higher-speed Access 
  Atiya_a_1991.pdf 6.10 Mb 00:28:15 00:14:31 00:12:42 00:06:21 00:00:32

Browse All Available ETDs by ( Author | Option )

If you have more questions or technical problems, please Contact the Caltech Library System.