Connectionism and Classical Conditioning
by Michael R.W. Dawson,
University of Alberta
Download/Read PDF | Add to Endnote
The purpose of this monograph is to examine the relationship between a particular artificial neural network, the perceptron, and the Rescorla-Wagner model of learning. It is shown that in spite of the fact that there is a formal equivalence between the two, they can make different predictions about the outcomes of a number of classical conditioning experiments. It is argued that this is due to algorithmic differences the two, differences which are separate from their computational equivalence.
Dawson, M. R. W. (2008). Connectionism and Classical Conditioning. Comparative Cognition & Behavior Reviews, 3. Retrieved from http://comparative-cognition-and-behavior-reviews.org/ doi:10.3819/ccbr.2008.30008