Affordable Access

Publisher Website

Using recurrent neural networks to learn the structure of interconnection networks

Authors
Journal
Neural Networks
0893-6080
Publisher
Elsevier
Volume
8
Issue
5
Identifiers
DOI: 10.1016/0893-6080(95)00025-u
Keywords
  • Technology And Applications

Abstract

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.

There are no comments yet on this publication. Be the first to share your thoughts.