Variable length chromosome GA for evolvable hardware

Abstract

This paper proposes the variable-length chromosome GA (VGA) for hardware evolution. VGA is introduced for the evolvable hardware (EHW) which can change its own hardware structure by genetic learning to adapt best to the environment. VGA makes it possible to evolve larger circuits more quickly than simple GAs. The improvements by VGAs are demonstrated by two experiments; one is the evolution of combinatorial circuits, the other is the evolution of pattern classifier functions used in the pattern recognition system for hand-written inputs.