Tech Report Available

[Clayton McMillan]

A compressed postscript version of the following tech report has been placed
in the pub/neuroprose directory for anonymous ftp from 
cheops.cis.ohio-state.edu (instructions follow).  This paper will 
appear in the Proceedings of the Thirteenth Annual Conference of the 
Cognitive Science Society.




                  The Connectionist Scientist Game: 
          Rule Extraction and Refinement in a Neural Network

          Clayton McMillan, Michael C. Mozer, & Paul Smolensky

                  Department of Computer Science and
                    Institute of Cognitive Science
                       University of Colorado
                       Boulder, CO 80309-0430

                    mcmillan at boulder.colorado.edu


                            Abstract

Scientific induction involves an iterative process of hypothesis formulation, 
testing, and refinement. People in ordinary life appear to undertake a similar 
process in explaining their world. We believe that it is instructive to study 
rule induction in connectionist systems from a similar perspective. We propose 
an approach, called the Connectionist Scientist Game, in which symbolic 
condition-action rules are extracted from the learned connection strengths in 
a network, thereby forming explicit hypotheses about a domain. The hypotheses 
are tested by injecting the rules back into the network and continuing the 
training process. This extraction-injection process continues until the 
resulting rule base adequately characterizes the domain. By exploiting 
constraints inherent in the domain of symbolic string-to-string mappings, we 
show how a connectionist architecture called RuleNet can induce explicit, 
symbolic condition-action rules from examples. RuleNet's performance is far 
superior to that of a variety of alternative architectures we've examined. 
RuleNet is capable of handling domains having both symbolic and subsymbolic 
components, and thus shows greater potential than purely symbolic learning 
algorithms. The formal string manipulation task performed by RuleNet can be 
viewed as an abstraction of several interesting cognitive models in the 
connectionist literature, including case role assignment and the mapping of 
orthography to phonology.


Instructions for porting the file and printing:

unix> ftp cheops.cis.ohio-state.edu

Connected to cheops.cis.ohio-state.edu.
220 cheops.cis.ohio-state.edu FTP server ready.
Name: anonymous
331 Guest login ok, send ident as password.
Password:neuron
230 Guest login ok, access restrictions apply.
ftp> binary
200 Type set to I.
ftp> cd pub/neuroprose
250 CWD command successful.
ftp> get mcmillan.csg.ps.Z
200 PORT command successful.
150 Opening BINARY mode data connection for mcmillan.csg.ps.Z (56880 bytes).
226 Transfer complete.
local: mcmillan.csg.ps.Z remote: mcmillan.csg.ps.Z
56880 bytes received in 2.5 seconds (22 Kbytes/s)
ftp> quit
221 Goodbye.

unix> uncompress mcmillan.csg.ps.Z
unix> lpr mcmillan.csg.ps

Clayton McMillan