CaltechTHESIS
  A Caltech Library Service

Learning algorithms for neural networks

Citation

Atiya, Amir (1991) Learning algorithms for neural networks. Dissertation (Ph.D.), California Institute of Technology. http://resolver.caltech.edu/CaltechETD:etd-09232005-083502

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.

Item Type:Thesis (Dissertation (Ph.D.))
Subject Keywords:backpropagation; clustering; convergence of neural networks; Hopfield model; oscillations; oscillations of neural networks; recurrent neural networks; stability of neural networks; training algorithms; unsupervised learning
Degree Grantor:California Institute of Technology
Division:Engineering and Applied Science
Major Option:Electrical Engineering
Thesis Availability:Public (worldwide access)
Research Advisor(s):
  • Abu-Mostafa, Yaser S.
Thesis Committee:
  • Abu-Mostafa, Yaser S. (chair)
  • Mead, Carver
  • Psaltis, Demetri
  • Posner, Edward C.
Defense Date:1 January 1991
Author Email:amir (AT) alumni.caltech.edu
Record Number:CaltechETD:etd-09232005-083502
Persistent URL:http://resolver.caltech.edu/CaltechETD:etd-09232005-083502
Default Usage Policy:No commercial reproduction, distribution, display or performance rights in this work are provided.
ID Code:3725
Collection:CaltechTHESIS
Deposited By: Imported from ETD-db
Deposited On:23 Sep 2005
Last Modified:26 Dec 2012 03:02

Thesis Files

[img]
Preview
PDF (Atiya_a_1991.pdf) - Final Version
See Usage Policy.

5Mb

Repository Staff Only: item control page