The evolution of parallel cellular machines: toward evolware.

The historical idea of evolving machines has recently resurfaced as the nascent field of bio-inspired systems and evolvable hardware. This paper describes the cellular programming approach used to evolve parallel cellular machines, presenting its application to six computational problems: density, synchronization, ordering, boundary computation, thinning and random number generation. Our results show that successful machines can be evolved to solve these tasks. The methodology described herein represents one possible approach to attaining truly evolving ware, evolware, with current implementations centering on hardware, while raising the possibility of using other forms in the future, such as bioware. The paper presents work in progress, the aim being to give an account of results obtained to date, ending with a list of several open issues for future research.

[1]  Zbigniew Michalewicz,et al.  Genetic algorithms + data structures = evolution programs (3rd ed.) , 1996 .

[2]  M Mitchell,et al.  The evolution of emergent computation. , 1995, Proceedings of the National Academy of Sciences of the United States of America.

[3]  James P. Crutchfield,et al.  Evolving Globally Synchronized Cellular Automata , 1995, ICGA.

[4]  Richard K. Belew,et al.  Towards a Self-Replicating Language for Computation , 1995, Evolutionary Programming.

[5]  Paula Gonzaga Sá,et al.  The Gacs-Kurdyumov-Levin automaton revisited , 1992 .

[6]  Moshe Sipper,et al.  Co-evolving cellular architectures by cellular programming , 1996, Proceedings of IEEE International Conference on Evolutionary Computation.

[7]  Moshe Sipper.  Quasi-Uniform Computation-Universal Cellular Automata , 1995, ECAL.

[8]  Young,et al.  Inferring statistical complexity. , 1989, Physical review letters.

[9]  Marco Tomassini,et al.  Evolutionary Algorithms , 1995, Towards Evolvable Hardware.

[10]  Moshe Sipper,et al.  Evolving Uniform and Non-Uniform Cellular Automata Networks , 1997 .

[11]  Stephen Wolfram,et al.  Universality and complexity in cellular automata , 1983 .

[12]  Marco Tomassini,et al.  Studying Probabilistic Faults in Evolved Non-Uniform Cellular Automata , 1996 .

[13]  Erick Cantú-Paz,et al.  A Summary of Research on Parallel Genetic Algorithms , 1995 .

[14]  Thomas Bäck,et al.  Evolutionary algorithms in theory and practice - evolution strategies, evolutionary programming, genetic algorithms , 1996 .

[15]  Vincenzo D'Andrea,et al.  CELLULAR AUTOMATA AS A COMPUTATIONAL MODEL FOR LOW-LEVEL VISION , 1993 .

[16]  Moshe Sipper,et al.  Non-uniform cellular automata: Evolution in rule space and formation of complex structures , 1994 .

[17]  Dietrich Stauffer,et al.  Anual Reviews of Computational Physics VII , 1994 .

[18]  Marco Tomassini,et al.  Generating Parallel Random Number Generators By Cellular Programming , 1996 .

[19]  Reiko Tanese,et al.  Parallel Genetic Algorithms for a Hypercube , 1987, ICGA.

[20]  Capcarrere,et al.  Two-state, r=1 Cellular Automaton that Classifies Density. , 1996, Physical review letters.

[21]  Dana S. Richards,et al.  Punctuated Equilibria: A Parallel Genetic Algorithm , 1987, ICGA.

[22]  F. H. Bennett,et al.  Discovery by genetic programming of a cellular automata rule that is better than any known rule for the majority classification problem , 1996 .

[23]  John H. Holland,et al.  Adaptation in Natural and Artificial Systems: An Introductory Analysis with Applications to Biology, Control, and Artificial Intelligence , 1992 .

[24]  Hans J. Herrmann,et al.  Cellular Automata for Elementary Image Enhancement , 1996, CVGIP Graph. Model. Image Process..

[25]  G. Y. Vichniac,et al.  Annealed and quenched inhomogeneous cellular automata (INCA) , 1986 .

[26]  Marco Tomassini,et al.  Designing cellular automata using a parallel evolutionary algorithm , 1997 .

[27]  S. K. Park,et al.  Random number generators: good ones are hard to find , 1988, CACM.

[28]  M. Sipper.  Co-evolving non-uniform cellular automata to perform computations , 1996 .

[29]  S. Wolfram.  Statistical mechanics of cellular automata , 1983 .

[30]  Moshe Sipper.  Studying artificial life using a simple, general cellular model , 1995 .

[31]  Bernard Manderick,et al.  Fine-Grained Parallel Genetic Algorithms , 1989, ICGA.

[32]  Marco Tomassini,et al.  Online Autonomous Evolware , 1996, ICES.

[33]  C. Adami,et al.  Introduction To Artificial Life , 1997, IEEE Trans. Evol. Comput..

[34]  Thomas Bäck,et al.  Evolutionary computation: Toward a new philosophy of machine intelligence , 1997, Complex..

[35]  Moshe Sipper.  An Introduction To Artificial Life , 1995 .

[36]  Vidroha Debroy,et al.  Genetic Programming , 1998, Lecture Notes in Computer Science.

[37]  Dorothea Heiss-Czedik,et al.  An Introduction to Genetic Algorithms. , 1997, Artificial Life.

[38]  Eduardo Sanchez.  Field Programmable Gate Array (FPGA) Circuits , 1995, Towards Evolvable Hardware.

[39]  Marco Tomassini,et al.  Co-evolving Parallel Random Number Generators , 1996, PPSN.

[40]  Zbigniew Michalewicz,et al.  Genetic Algorithms + Data Structures = Evolution Programs , 1996, Springer Berlin Heidelberg.

[41]  Zicheng Guo,et al.  Parallel thinning with two-subiteration algorithms , 1989, Commun. ACM.

[42]  Marco Tomassini,et al.  Towards Evolvable Hardware: The Evolutionary Engineering Approach , 1996 .

[43]  J. Crutchfield,et al.  Turbulent pattern bases for cellular automata , 1993 .

[44]  James P. Crutchfield,et al.  Dynamics, computation, and the “edge of chaos”: a re-examination , 1993, adap-org/9306003.

[45]  David B. Fogel,et al.  Evolutionary Computation: Towards a New Philosophy of Machine Intelligence , 1995 .

[46]  Moshe Sipper,et al.  Designing Evolware by Cellular Programming , 1996, ICES.

[47]  Tommaso Toffoli,et al.  Cellular Automata Machines , 1987, Complex Syst..

[48]  Moshe Sipper,et al.  Co-evolving architectures for cellular machines , 1997 .

[49]  Howard C. Card,et al.  Parallel Random Number Generation for VLSI Systems Using Cellular Automata , 1989, IEEE Trans. Computers.

[50]  James P. Crutchfield,et al.  A Genetic Algorithm Discovers Particle-Based Computation in Cellular Automata , 1994, PPSN.

[51]  James P. Crutchfield,et al.  Revisiting the Edge of Chaos: Evolving Cellular Automata to Perform Computations , 1993, Complex Syst..

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

[53]  Peter Gacs.  Nonergodic one-dimensional media and reliable computation , 1985 .

[54]  J. Crutchfield,et al.  The attractor—basin portrait of a cellular automaton , 1992 .

[55]  S. Wolfram.  Random sequence generation by cellular automata , 1986 .

[56]  Marco Tomassini,et al.  a Survey of Genetic Algorithms , 1995 .

[57]  L. Darrell Whitley,et al.  Optimization Using Distributed Genetic Algorithms , 1990, PPSN.

[58]  Land,et al.  No perfect two-state cellular automata for density classification exists. , 1995, Physical review letters.

[59]  Marco Tomassini,et al.  The Parallel Genetic Cellular Automata: Application to Global Function Optimization , 1993 .

[60]  Melanie Mitchell,et al.  Evolving cellular automata to perform computations: mechanisms and impediments , 1994 .