The FAST Architecture: A Neural Network with Flexible Adaptable-Size Topology

Authors:
Andres Pérez;Eduardo Sanchez
Affiliations:
-;-
Venue:
MICRONEURO '96 Proceedings of the 5th International Conference on Microelectronics for Neural Networks and Fuzzy Systems
Year:
1996

Citing 0
Cited 2

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

Quantified Score

Hi-index	0.00

Visualization

Abstract

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.