NIPS preprint available via neuroprose

[Sreerupa Das]

FTP-host: archive.cis.ohio-state.edu
FTP-filename: /pub/neuroprose/das.dolce.ps.Z
Number of pages: 8

The following paper is now available for copying from
the Neuroprose archive.  Only electronic version of this paper is
available.  This is a preprint of the paper to appear in J.D. Cowan,
G. Tesauro, and J.  Alspector (eds.) Advances in Neural Information
Processing Systems 6, 1994.



	A Unified Gradient-Descent/Clustering Architecture for
		   Finite State Machine Induction

	       	Sreerupa Das  and  Michael C. Mozer
	          Department of Computer Science
	       	University of Colorado at Boulder
		         CO 80309--0430


			   ABSTRACT

Although recurrent neural nets have been moderately successful in
learning to emulate finite-state machines (FSMs), the continuous
internal state dynamics of a neural net are not well matched to the
discrete behavior of an FSM.  We describe an architecture, called
DOLCE, that allows discrete states to evolve in a net as learning
progresses.  DOLCE consists of a standard recurrent neural net trained
by gradient descent and an adaptive clustering technique that
quantizes the state space.  DOLCE is based on the assumption that a
finite set of discrete internal states is required for the task, and
that the actual network state belongs to this set but has been
corrupted by noise due to inaccuracy in the weights.  DOLCE learns to
recover the discrete state with maximum a posteriori probability from
the noisy state.  Simulations show that DOLCE leads to a significant
improvement in generalization performance over earlier neural net
approaches to FSM induction.

======================================================================
 FTP procedure:

unix> ftp archive.cis.ohio-state.edu (or 128.146.8.52)
Name: anonymous
Password: your_email_address
ftp> cd pub/neuroprose
ftp> binary
ftp> get das.dolce.ps.Z
ftp> quit
unix> uncompress das.dolce.ps.Z
unix> lpr das.dolce.ps



Thanks to Jordan Pollack for maintaining the archive!

Sreerupa Das 
Department of Computer Science 
University of Colorado at Boulder
CO 80309-0430 					email: rupa at cs.colorado.edu