Self-organising neural networks for adaptive control

The objective of the Hybrid Learning System (HLS) is to achieve preset targets by evolving a behavioral repertoire that efficiently explores and exploits the problem environment. Feature maps encode two types of knowledge within HLS; long-term memory traces of useful regularities within the environment and the classifier performance data calibrated against an object's feature states and targets. Self-organization of these networks constitutes non-genetic-based (experience-driven) learning within HLS. This article presents a description of the HLS and an analysis of the modified feature map implementing associative memory. Initial results are presented that demonstrate the behavior of the system of a simple control task.