Using Extra Output Learning to Insert a Symbolic Theory into a Connectionist Network

  • Authors:

  • M. R. W. Dawson;D. A. Medler;D. B. Mccaughan;L. Willson;M. Carbonaro

  • Affiliations:

  • Department of Psychology, University of Alberta, Edmonton, Alberta, Canada T6G 2E9 (E-mail: mike@bcp.psych.ualberta.ca)/;Center for the Neural Basis of Cognition, Carnegie Mellon University, 115 Mellon Institute, 4400 Fifth Avenue, Pittsburgh, PA 15213 USA/;Department of Computing Science, University of Alberta, Edmonton, Alberta, Canada T6G 2E9/;Department of Psychology, University of Alberta, Edmonton, Alberta, Canada T6G 2E9/;Department of Educational Psychology, University of Alberta, Edmonton, Alberta, Canada T6G 2E9

  • Venue:
  • Minds and Machines
  • Year:
  • 2000

Quantified Score

Hi-index 0.00

Visualization

Abstract

This paper examines whether a classical model could be translated into a PDP network using a standard connectionist training technique called extra output learning. In Study 1, standard machine learning techniques were used to create a decision tree that could be used to classify 8124 different mushrooms as being edible or poisonous on the basis of 21 different Features (Schlimmer, 1987). In Study 2, extra output learning was used to insert this decision tree into a PDP network being trained on the identical problem. An interpretation of the trained network revealed a perfect mapping from its internal structure to the decision tree, representing a precise translation of the classical theory to the connectionist model. In Study 3, a second network was trained on the mushroom problem without using extra output learning. An interpretation of this second network revealed a different algorithm for solving the mushroom problem, demonstrating that the Study 2 network was indeed a proper theory translation.