Elementary encoding by evolutionary approach
ICCSA'03 Proceedings of the 2003 international conference on Computational science and its applications: PartI
A comparison of different circuit representations for evolutionary analog circuit design
ICES'03 Proceedings of the 5th international conference on Evolvable systems: from biology to hardware
Using negative correlation to evolve fault-tolerant circuits
ICES'03 Proceedings of the 5th international conference on Evolvable systems: from biology to hardware
Research on multi-objective on-line evolution technology of digital circuit based on FPGA model
ICES'07 Proceedings of the 7th international conference on Evolvable systems: from biology to hardware
Autonomic fault-handling and refurbishment using throughput-driven assessment
Applied Soft Computing
Consensus-Based evaluation for fault isolation and on-line evolutionary regeneration
ICES'05 Proceedings of the 6th international conference on Evolvable Systems: from Biology to Hardware
| Hi-index | 0.00 |
Evolutionary algorithms (EAs) have been widely used in evolvable hardware. The very term, evolvable hardware, reflects the importance and omnitude of EAs in this field. However, EAs have primarily been used as an optimisation or search tool, which can explore a large and complex space. While success has been demonstrated by EAs in exploring unconventional designs that are hard to reach by human experts, it is interesting to ask the question whetherwe have fully used all the potentialities of EAs. We argue in this paper that there is rich information in a population which can and should be exploited. The classical approach of evolving the best individual in a population may not be the best one. A truly population-based approach that emphasizes population rather than the best individual can often bring in several important benefits to evolvable hardware, including efficiency, accuracy, adaptiveness, andfault-tolerance.