Multiple Interacting Programs: a Representation for Evolving Complex Behavior

This paper defines a representation for expressing complex behaviors called multiple interacting programs MIPs and describes an evolutionary method for evolving solutions to difficult problems expressed as MIPs structures. The MIPs representation is a generalization of neural network architectures that can model any type of dynamic system. The evolutionary training method described is based on an evolutionary program originally used to evolve the architecture and weights of recurrent neural networks. Example experiments demonstrate the training method's ability to evolve appropriate MIPs solutions for difficult problems. An analysis of the evolved solutions shows their dynamics to be interesting and nontrivial.

[1]  Lawrence Davis,et al.  Training Feedforward Neural Networks Using Genetic Algorithms , 1989, IJCAI.

[2]  Byoung-Tak Zhang,et al.  Evolutionary Induction of Sparse Neural Trees , 1997, Evolutionary Computation.

[3]  Peter J. Angeline,et al.  An evolutionary algorithm that constructs recurrent neural networks , 1994, IEEE Trans. Neural Networks.

[4]  Riccardo Poli,et al.  Evolution of Graph-Like Programs with Parallel Distributed Genetic Programming , 1997, ICGA.

[5]  Richard K. Belew,et al.  Evolving networks: using the genetic algorithm with connectionist learning , 1990 .

[6]  Kurt Hornik,et al.  Multilayer feedforward networks are universal approximators , 1989, Neural Networks.

[7]  L. Darrell Whitley,et al.  Genetic algorithms and neural networks: optimizing connections and connectivity , 1990, Parallel Comput..

[8]  Nichael Lynn Cramer,et al.  A Representation for the Adaptive Generation of Simple Sequential Programs , 1985, ICGA.

[9]  Hiroaki Kitano,et al.  Designing Neural Networks Using Genetic Algorithms with Graph Generation System , 1990, Complex Syst..

[10]  Kurt Hornik,et al.  FEED FORWARD NETWORKS ARE UNIVERSAL APPROXIMATORS , 1989 .

[11]  Peter J. Angeline Benefits of distributed solutions when evolving symbolic equations , 1997, Optics & Photonics.

[12]  Frédéric Gruau,et al.  Genetic micro programming of neural networks , 1994 .

[13]  G. Kane Parallel Distributed Processing: Explorations in the Microstructure of Cognition, vol 1: Foundations, vol 2: Psychological and Biological Models , 1994 .

[14]  Lee Spector,et al.  Evolving teamwork and coordination with genetic programming , 1996 .

[15]  P. Angeline An Investigation into the Sensitivity of Genetic Programming to the Frequency of Leaf Selection Duri , 1996 .

[16]  Sandip Sen,et al.  Crossover Operators for Evolving A Team , 1997 .

[17]  Una-May O'Reilly,et al.  A comparative analysis of genetic programming , 1996 .

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

[19]  Peter J. Angeline,et al.  A Comparative Analysis of Genetic Programming , 1996 .

[20]  Peter J. Angeline,et al.  Two self-adaptive crossover operators for genetic programming , 1996 .

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

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

[23]  Randall D. Beer,et al.  Evolving Dynamical Neural Networks for Adaptive Behavior , 1992, Adapt. Behav..

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

[25]  James L. McClelland,et al.  Parallel distributed processing: explorations in the microstructure of cognition, vol. 1: foundations , 1986 .

[26]  Una-May O'Reilly,et al.  Genetic Programming II: Automatic Discovery of Reusable Programs. , 1994, Artificial Life.

[27]  Lawrence J. Fogel,et al.  Artificial Intelligence through Simulated Evolution , 1966 .

[28]  Astro Teller,et al.  Neural Programming and an Internal Reinforcement Policy , 1996 .

[29]  Astro Teller,et al.  The evolution of mental models , 1994 .