Evolving hardware with genetic learning: a first step towards building a Darwin machine
Proceedings of the second international conference on From animals to animats 2 : simulation of adaptive behavior: simulation of adaptive behavior
Evolving Hardware with Self-reconfigurable connectivity in Xilinx FPGAs
AHS '06 Proceedings of the first NASA/ESA conference on Adaptive Hardware and Systems
Virtual reconfigurable circuits for real-world applications of evolvable hardware
ICES'03 Proceedings of the 5th international conference on Evolvable systems: from biology to hardware
Explorations in design space: unconventional electronics designthrough artificial evolution
IEEE Transactions on Evolutionary Computation
| Hi-index | 0.00 |
In this paper we propose three small instances of a reconfigurable circuit and analyze their properties using the brute force method and evolutionary algorithm. Although proposed circuits are very similar, significant differences were demonstrated, namely in the number of unique designs they can implement, the sensitiveness of functions to the inversions in the configuration bitstream and the average number of generations needed to find a target function. These findings are quite unintuitive. Once important (sensitive) bits of the reconfigurable circuit are identified, evolutionary algorithm can incorporate this knowledge. We believe that the proposed type of analysis can help those designers who develop new reconfigurable circuits for evolvable hardware applications.