EVOLVED DUAL WEIGHT NEURAL ARCHITECTURES TO FACILITATE INCREMENTAL LEARNING
John A. Bullinaria · 2009
This paper explores techniques for improving incremental learning performance for generalization tasks. The idea is to generalize well from past input-output mappings that become available in batches over time, without the need to store past batches. Standard connectionist systems have previously been optimized for this problem using an evolutionary computation approach. Here that approach is explored more generally and rigorously, and dual weight architectures are incorporated into the evolutionary neural network approach and shown to result in improved performance over existing incremental learning systems. 1