On-line Adaptation of Neural Networks with Evolvable Hardware

This paper describes an evolvable hardware (EHW) system for generalized neural network learning. We have developed an ASIC VLSI chip, which is a building block to congure a scalable neural network hardware system. In our system, both the topology and the hidden layer node functions of a neural network mapped on the chips are dynamically changed using a genetic algorithm. Thus, the most desirable network topology and choice of node function (e.g. Gaussian or sigmoid) for a given application can be determined adaptively. This approach is particularly suited to applications requiring ability to cope with time-varying problems and realtime timing constraints. The chip consists of 15 Digital Signal Processors (DSPs), whose functions and interconnections are recon gured dynamically according to the chromosomes of the genetic algorithm. Incorporation of local learning hardware increases the learning speed signi cantly. Simulation results on the prediction of chaotic data and adaptive equalization in digital mobile communication are also given. Our system is two orders of magnitude faster than a Sun SS20 on the corresponding problem.