LoboVault Home

Gradient-like dynamics in neural networks


Please use this identifier to cite or link to this item: http://hdl.handle.net/1928/20415

Gradient-like dynamics in neural networks

Show full item record

Title: Gradient-like dynamics in neural networks
Author: Abdallah, Chaouki T.; Howse, James W.; Heileman, Gregory L.
Abstract: This report presents a formalism that enables the dynamics of a broad class of neural networks to be understood. A number of previous works have analyzed the Lyapunov stability of neural network models. This type of analysis shows that the excursion of the solutions from a stable point is bounded. The purpose of this work is to present a model of the dynamics that also describes the phase space behavior as well as the structural stability of the system. This is achieved by writing the general equations of the neural network dynamics as a gradient-like system. In this paper some important properties of gradient-like systems are developed and then it is demonstrated that a broad class of neural network models are expressible in this form.
Date: 2012-04-19
Description: UNM Technical Report No. EECE93 001
URI: http://hdl.handle.net/1928/20415

Files in this item

Files Size Format View
Abdallah Howse ... ics in neural networks.pdf 1.629Mb PDF View/Open

This item appears in the following Collection(s)

Show full item record

UNM Libraries

Search LoboVault


My Account