Evolution and learning for digital circuit design
Alexander Nicholson · 2000
We investigate the use of learning and evolution for digital hardware design. Using the reactive tabu search for discrete optimization, we show that we can learn a multiplier circuit from a set of examples. The learned circuit makes less than 2% error and uses fewer chip resources than the standard digital design. We compare use of a genetic algorithm and the reactive tabu search for fitness optimization. On a 2-bit adder design problem, the reactive tabu search performs significantly better for a similar execution time.