Reduction of catastrophic forgetting in multilayer neural networks trained by contrastive Hebbian Learning with pseudorehearsal

Abstract

Neural networks encounter serious catastrophic forgetting or catastrophic interference when information is learned sequentially. One of the solutions to this problem is pseudorehearsal, in which pseudopatterns are learned with training patterns. This method has shown superior performance for multilayer neural networks trained by the backpropagation algorithm. However, the backpropagation algorithm is biologically implausible because it requires passage of information backward from output neurons to input ones. On the other hand, Contrastive Hebbian Learning (CHL) is a learning method using Hebbian rule for synaptic weight changes. Since Hebbian learning can be performed locally between two neurons and doesn't need to take into account the overall input-output for the network, it is much more biologically plausible than the backpropagation algorithm. In this paper, we examine characteristics of multilayer neural networks trained by CHL with pseudorehearsal when information is applied sequentially, and how catastrophic forgetting can be reduced.