Title

Using Recurrent Neural Networks To Learn The Structure Of Interconnection Networks

Keywords

Finite-State automata; Interconnection networks; Knowledge extraction; Real-Time training; Recurrent networks; Sequential machines

Abstract

A modified Recurrent Neural Network (RNN) is used to learn a Self-Routing Interconnection Network (SRIN) from a set of routing examples. The RNN is modified so that it has several distinct initial states. This is equivalent to a single RNN learning multiple different synchronous sequential machines. We define such a sequential machine structure as augmented and show that a SRIN is essentially an Augmented Synchronous Sequential Machine (ASSM). As an example, we learn a small six-switch SRIN. After training we extract the network's internal representation of the ASSM and corresponding SRIN. © 1995.

Publication Date

1-1-1995

Publication Title

Neural Networks

Volume

8

Issue

5

Number of Pages

793-804

Document Type

Article

Personal Identifier

scopus

DOI Link

https://doi.org/10.1016/0893-6080(95)00025-U

Socpus ID

0028852020 (Scopus)

Source API URL

https://api.elsevier.com/content/abstract/scopus_id/0028852020

This document is currently not available here.

Share

COinS