Using Recurrent Neural Networks To Learn The Structure Of Interconnection Networks

    Authors

    M. W. Goudreau;C. L. Giles

    Comments

    Authors: contact us about adding a copy of your work at STARS@ucf.edu

    Abbreviated Journal Title

    Neural Netw.

    Keywords

    INTERCONNECTION NETWORKS; RECURRENT NETWORKS; REAL-TIME TRAINING; KNOWLEDGE EXTRACTION; SEQUENTIAL MACHINES; FINITE-STATE AUTOMATA; ARCHITECTURE; COMPLEXITY; INDUCTION; Computer Science, Artificial Intelligence

    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.

    Journal Title

    Neural Networks

    Volume

    8

    Issue/Number

    5

    Publication Date

    1-1-1995

    Document Type

    Article

    Language

    English

    First Page

    793

    Last Page

    804

    WOS Identifier

    WOS:A1995TB35600011

    ISSN

    0893-6080

    Share

    COinS