CaltechTHESIS
  A Caltech Library Service

Neural network design for switching network control

Citation

Brown, Timothy X. (1991) Neural network design for switching network control. Dissertation (Ph.D.), California Institute of Technology. http://resolver.caltech.edu/CaltechTHESIS:03142014-142621814

Abstract

A neural network is a highly interconnected set of simple processors. The many connections allow information to travel rapidly through the network, and due to their simplicity, many processors in one network are feasible. Together these properties imply that we can build efficient massively parallel machines using neural networks. The primary problem is how do we specify the interconnections in a neural network. The various approaches developed so far such as outer product, learning algorithm, or energy function suffer from the following deficiencies: long training/ specification times; not guaranteed to work on all inputs; requires full connectivity.

Alternatively we discuss methods of using the topology and constraints of the problems themselves to design the topology and connections of the neural solution. We define several useful circuits-generalizations of the Winner-Take-All circuitthat allows us to incorporate constraints using feedback in a controlled manner. These circuits are proven to be stable, and to only converge on valid states. We use the Hopfield electronic model since this is close to an actual implementation. We also discuss methods for incorporating these circuits into larger systems, neural and nonneural. By exploiting regularities in our definition, we can construct efficient networks. To demonstrate the methods, we look to three problems from communications. We first discuss two applications to problems from circuit switching; finding routes in large multistage switches, and the call rearrangement problem. These show both, how we can use many neurons to build massively parallel machines, and how the Winner-Take-All circuits can simplify our designs.

Next we develop a solution to the contention arbitration problem of high-speed packet switches. We define a useful class of switching networks and then design a neural network to solve the contention arbitration problem for this class. Various aspects of the neural network/switch system are analyzed to measure the queueing performance of this method. Using the basic design, a feasible architecture for a large (1024-input) ATM packet switch is presented. Using the massive parallelism of neural networks, we can consider algorithms that were previously computationally unattainable. These now viable algorithms lead us to new perspectives on switch design.

Item Type:Thesis (Dissertation (Ph.D.))
Subject Keywords:Electrical Engineering ; Neural network design ; switching network control
Degree Grantor:California Institute of Technology
Division:Engineering and Applied Science
Major Option:Electrical Engineering
Thesis Availability:Public (worldwide access)
Research Advisor(s):
  • Posner, Edward C.
Thesis Committee:
  • Unknown, Unknown
Defense Date:29 June 1990
Non-Caltech Author Email:timxb (AT) colorado.edu
Record Number:CaltechTHESIS:03142014-142621814
Persistent URL:http://resolver.caltech.edu/CaltechTHESIS:03142014-142621814
Default Usage Policy:No commercial reproduction, distribution, display or performance rights in this work are provided.
ID Code:8136
Collection:CaltechTHESIS
Deposited By: Dan Anguka
Deposited On:14 Mar 2014 22:50
Last Modified:14 Mar 2014 22:50

Thesis Files

[img]
Preview
PDF - Final Version
See Usage Policy.

3004Kb

Repository Staff Only: item control page