Exploring knowledge schemes for efficient evolution of hardware

There exist several approaches to improve the quality of evolution. In this paper, a priori design knowledge as a part of evolving systems is discussed. Further, experiments are reported showing how a priori knowledge (data buses and reuse) can be beneficial compared to gate level design of multiplier circuits. The future goal of the work is to be able to evolve systems for complex real-world applications (image and signal processing).

[1]  Julian Francis Miller,et al.  Towards the automatic design of more efficient digital circuits , 2000, Proceedings. The Second NASA/DoD Workshop on Evolvable Hardware.

[2]  Jim Torresen,et al.  Possibilities and Limitations of Applying Evolvable Hardware to Real-World Applications , 2000, FPL.

[3]  W. Daniel Hillis,et al.  Co-evolving parasites improve simulated evolution as an optimization procedure , 1990 .

[4]  Xin Yao,et al.  Automatic modularization by speciation , 1996, Proceedings of IEEE International Conference on Evolutionary Computation.

[5]  John R. Koza,et al.  The importance of reuse and development in evolvable hardware , 2003, NASA/DoD Conference on Evolvable Hardware, 2003. Proceedings..

[6]  J. Tørresen,et al.  Increased complexity evolution applied to evolvable hardware , 1999 .

[7]  Jim Torresen,et al.  Evolving Multiplier Circuits by Training Set and Training Vector Partitioning , 2003, ICES.

[8]  Erick Cantú-Paz,et al.  A Survey of Parallel Genetic Algorithms , 2000 .

[9]  Tatiana Kalganova,et al.  Bidirectional incremental evolution in extrinsic evolvable hardware , 2000, Proceedings. The Second NASA/DoD Workshop on Evolvable Hardware.

[10]  Hitoshi Iba,et al.  A Pattern Recognition System Using Evolvable Hardware , 1996, PPSN.

[11]  Julian Francis Miller,et al.  Principles in the Evolutionary Design of Digital Circuits—Part II , 2000, Genetic Programming and Evolvable Machines.

[12]  John Hallam,et al.  Learning Complex Robot Behaviours by Evolutionary Computing with Task Decomposition , 1997, EWLR.

[13]  Mitchell A. Potter,et al.  EVOLVING NEURAL NETWORKS WITH COLLABORATIVE SPECIES , 2006 .

[14]  Isamu Kajitani,et al.  Hardware Evolution at Function Level , 1996, PPSN.

[15]  John R. Koza,et al.  Genetic programming 2 - automatic discovery of reusable programs , 1994, Complex Adaptive Systems.

[16]  David E. Goldberg,et al.  Genetic Algorithms in Search Optimization and Machine Learning , 1988 .

[17]  Jim Torresen.  A Dynamic Fitness Function Applied to Improve the Generalisation when Evolving a Signal Processing Hardware Architecture , 2002, EvoWorkshops.

[18]  Kenneth A. De Jong,et al.  Evolving Complex Structures via Cooperative Coevolution , 1995, Evolutionary Programming.

[19]  Jim Tørresen.  Evolving both Hardware Subsystems and the Selection of Variants of such into an Assembled System , 2002, ESM.

[20]  Jim Torresen,et al.  Two-Step Incremental Evolution of a Prosthetic Hand Controller Based on Digital Logic Gates , 2001, ICES.

[21]  Xin Yao,et al.  Promises and challenges of evolvable hardware , 1996, IEEE Trans. Syst. Man Cybern. Part C.

[22]  Jim Tørresen,et al.  A Divide-and-Conquer Approach to Evolvable Hardware , 1998, ICES.

[23]  Jim Torresen,et al.  Scalable evolvable hardware applied to road image recognition , 2000, Proceedings. The Second NASA/DoD Workshop on Evolvable Hardware.