Searching neural network structures with L systems and genetic algorithms

We present a new method for using genetic algorithms and L systems to grow up efficient neural network structures. Our L rules operate directly on 2-dimensional cell matrix. Lrules are produced automatically by genetic algorithm and they have“age”that controls the number of firing times, i.e., times we can apply each rule. We have modified the conventional neural network model so that it is easy to present the knowledge by birth (axon weights) and the learning by experience (dendrite weights). A connection is shown to exist between the axon weights and learning parameters used e.g., in back propagation. This system enables us to find special structures that are very fast for both to train and to operate comparing to conventional, layered methods.

[1]  Frank Dellaert,et al.  Toward an evolvable model of development for autonomous agent synthesis , 1994 .

[2]  Grzegorz Rozenberg,et al.  The mathematical theory of L systems , 1980 .

[3]  W S McCulloch,et al.  A logical calculus of the ideas immanent in nervous activity , 1990, The Philosophy of Artificial Intelligence.

[4]  Michael de la Maza,et al.  Book review: Genetic Algorithms + Data Structures = Evolution Programs by Zbigniew Michalewicz (Springer-Verlag, 1992) , 1993 .

[5]  Idan Segev.  Single neurone models: oversimple, complex and reduced , 1992, Trends in Neurosciences.

[6]  Aristid Lindenmayer,et al.  Mathematical Models for Cellular Interactions in Development , 1968 .

[7]  R. Belew.  Interposing an ontogenic model between Genetic Algorithms and Neural Networks , 1992 .

[8]  Jari Vaario.  An emergent modeling method for artificial neural networks , 1994 .

[9]  Simon M. Lucas.  Evolving neural network learning behaviours with set-based chromosomes , 1996, ESANN.

[10]  Grzegorz Rozenberg,et al.  Developmental systems and languages , 1972, STOC.

[11]  Jean-Arcady Meyer,et al.  Evolution and development of control architectures in animats , 1995, Robotics Auton. Syst..

[12]  R. Palmer,et al.  Introduction to the theory of neural computation , 1994, The advanced book program.

[13]  M. Alexander,et al.  Principles of Neural Science , 1981 .

[14]  R. Richter,et al.  Principles of Neural Science, 3rd edition , 1993 .

[15]  Zbigniew Michalewicz,et al.  Genetic Algorithms + Data Structures = Evolution Programs , 1992, Artificial Intelligence.

[16]  A. Lindenmayer.  Mathematical models for cellular interactions in development. I. Filaments with one-sided inputs. , 1968, Journal of theoretical biology.

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

[18]  Richard K. Belew,et al.  Interposing an Ontogenetic Model Between Genetic Algorithms and Neural Networks , 1992, NIPS.

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

[20]  S. Hyakin,et al.  Neural Networks: A Comprehensive Foundation , 1994 .

[21]  A. Cangelosi,et al.  Cell division and migration in a 'genotype' for neural networks (Cell division and migration in neural networks) , 1993 .

[22]  Marvin Minsky,et al.  Computation : finite and infinite machines , 2016 .