Sub-machine-code GP: New Results and Extensions

Sub-machine-code GP (SMCGP) is a technique to speed up genetic programming (GP) and to extend its scope based on the idea of exploiting the internal parallelism of sequential CPUs. In previous work [20] we have shown examples of applications of this technique to the evolution of parallel programs and to the parallel evaluation of 32 or 64 fitness cases per program execution in Boolean classification problems. After recalling the basic features of SMCGP, in this paper we first apply this technique to the problem of evolving parallel binary multipliers.s.Then we describe how SMCGP can be extended to process multiple fitness cases per program execution in continuous symbolic regression problems where inputs and outputs are real-valued numbers, reporting experimental results on a quartic polynomial approximation task.

[1]  Riccardo Poli,et al.  Sub-machine-code genetic programming , 1999 .

[2]  Peter Nordin,et al.  Genetic programming - An Introduction: On the Automatic Evolution of Computer Programs and Its Applications , 1998 .

[3]  Peter Nordin,et al.  Evolutionary program induction of binary machine code and its applications , 1997 .

[4]  Riccardo Poli,et al.  Schema Theory for Genetic Programming with One-Point Crossover and Point Mutation , 1997, Evolutionary Computation.

[5]  John R. Koza,et al.  Genetic programming - on the programming of computers by means of natural selection , 1993, Complex adaptive systems.

[6]  Julian F. Miller,et al.  Evolving Digital Logic Circuits on Xilinx 6000 Family FPGAs , 1998 .

[7]  Peter Nordin,et al.  A compiling genetic programming system that directly manipulates the machine-code , 1994 .

[8]  P. K. Chawdhry,et al.  Soft Computing in Engineering Design and Manufacturing , 1998, Springer London.

[9]  A. Fukunaga,et al.  A Genome Complier for High-Performance Genetic Programming , 1998 .

[10]  John R. Koza,et al.  Parallel genetic programming: a scalable implementation using the transputer network architecture , 1996 .

[11]  Simon Handley,et al.  On the use of a directed acyclic graph to represent a population of computer programs , 1994, Proceedings of the First IEEE Conference on Evolutionary Computation. IEEE World Congress on Computational Intelligence.

[12]  W. Langdon.  An Analysis of the MAX Problem in Genetic Programming , 1997 .

[13]  Hitoshi Iba,et al.  Genetic Programming 1998: Proceedings of the Third Annual Conference , 1999, IEEE Trans. Evol. Comput..

[14]  Astro Teller,et al.  Automatically Choosing the Number of Fitness Cases: The Rational Allocation of Trials , 1997 .

[15]  Peter Ross,et al.  Tackling the Boolean Even N Parity Problem with Genetic Programming and Limited-Error Fitness , 1997 .

[16]  John R. Koza,et al.  Genetic programming 1997 : proceedings of the Second Annual Conference, July 13-16, 1997, Stanford University , 1997 .

[17]  Lee Spector,et al.  High-performance, parallel, stack-based genetic programming , 1996 .

[18]  Jordan B. Pollack,et al.  Massively parallel genetic programming , 1996 .

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

[20]  Peter Nordin,et al.  Evolving Turing-Complete Programs for a Register Machine with Self-modifying Code , 1995, ICGA.