Connectionism and Classical Conditioning
Michael R. W. Dawson · Comparative Cognition & Behavior Reviews · 2008
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 between the two, differences which are separate from their computational equivalence.