Using Recurrent Neural Networks to Learn the Structure of
Interconnection Networks
Using Recurrent Neural Networks to Learn the Structure of
Interconnection Networks
Files
Publication or External Link
Date
1998-10-15
Authors
Goudreau, Mark W.
Giles, C. Lee
Advisor
Citation
DRUM DOI
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.
(Also cross-referenced as UMIACS-TR-94-20.)