A non-computationally-intensive neurocontroller for autonomous mobile robot navigation
Biologically inspired robot behavior engineering
Self-organizing state aggregation for architecture design of Q-learning
Information Sciences: an International Journal
Hi-index | 0.00 |
One of the central problems in the application of neural networks is finding the optimal network topology. This paper introduces the FAST architecture (Flexible Adaptable-Size Topology), an on-line, evoloving neural network that dinamically adapts its topology through interactions with a problem- specific environment. We present a fully digital implementation of the network and demonstrate its viability on a pattern clustering task. We believe the FAST architecture holds potential by offering a fast, flexible platform for neural network applications.