Abstract--- Genetic programming has been successfully applied to evolve computer programs for solving a variety of interesting problems. In the previous work we introduced the breeder genetic programming (BGP) method that has Occam's razor in its fitness measure to evolve minimal size multilayer perceptrons. In this paper we apply the method to synthesis of sigma-pi neural networks. Unlike perceptron architectures, sigma-pi networks use product units as well as summation units to build higher-order terms. The effectiveness of the method is demonstrated on benchmark problems. Simulation results on noisy data suggest that BGP not only improves the generalization performance, it can also accelerate the convergence speed. I.
|
4828
|
Genetic Algorithms
– Goldberg
- 1989
|
|
1782
|
Genetic Programming: On the Programming of Computers by Means of Natural Selection Cambridge
– Koza
- 1992
|
|
1316
|
Genetic Algorithms + Data Structures = Evolution Programs. AI Series
– Michalewicz
- 1992
|
|
363
|
Perceptrons : An Introduction to Computational Geometry
– Papert
- 1969
|
|
268
|
An overview of evolutionary algorithms for parameter optimization
– Back, Schwefel
- 1993
|
|
250
|
Designing neural network using genetic algorithm with graph generation system
– Kitano
- 1990
|
|
241
|
Predictive models for the breeder genetic algorithm
– Mühlenbein, Schlierkamp-Vose
- 1993
|
|
194
|
Connectionist models and their properties
– Feldman, Ballard
- 1982
|
|
185
|
Designing neural networks using genetic algorithms
– F, Todd, et al.
- 1989
|
|
127
|
Competitive environments evolve better solutions for complex tasks
– Angeline, Pollack
- 1993
|
|
101
|
Genetic algorithms and neural networks: Optimizing connections and connectivity
– Whitley, Starkweather, et al.
- 1990
|
|
85
|
Towards the Genetic Synthesis of neural networks
– Harp, Samad, et al.
- 1989
|
|
80
|
A general framework for Parallel Distributed Processing
– Rumelhart, Hinton, et al.
- 1986
|
|
80
|
Genetic programming for feature discovery and image discrimination
– Tackett
- 1993
|
|
79
|
Programming: The Movie
– Koza, Rice
- 1992
|
|
70
|
Product units: A computationally powerful and biologically plausible extension to backpropagation networks
– R, Rumelhart
- 1989
|
|
47
|
Learning, invariance, and generalization in highorder neural networks
– Giles, Maxwell
- 1987
|
|
42
|
Genetic synthesis of Boolean neural networks with a cell rewriting developmental process
– Gruau
- 1992
|
|
32
|
Polynomial theory of complex systems
– Ivakhnenko
- 1971
|
|
28
|
Parallel genetic algorithm in combinatorial optimization
– Mühlenbein
- 1992
|
|
26
|
Accelerated learning by active example selection
– Zhang
- 1994
|
|
25
|
Evolution in time and space-The parallel genetic algorithm
– Muhlenbein
- 1991
|
|
25
|
Genetic Programming of Minimal Neural Nets Using Occam's Razor
– Zhang, Muehlenbein
- 1993
|
|
25
|
Evolving optimal neural networks using genetic algorithms with Occam's razor
– Zhang, Muhlenbein
- 1993
|
|
24
|
Studies in Artificial Evolution
– Collins
- 1992
|
|
18
|
System identification using structured genetic algorithms
– Iba, Kurita, et al.
- 1993
|
|
16
|
Dualistic geometry of the manifold of higher-order neurons
– Amari
- 1991
|
|
15
|
Evolutionary algorithms: theory and applications
– Mühlenbein
- 1993
|
|
12
|
System identification with evolving polynomial networks
– Kargupta, Smith
- 1991
|
|
7
|
A quantitative Occam's razor
– Sorkin
- 1983
|
|
7
|
Learning by Genetic Neural Evolution
– Zhang
- 1992
|
|
6
|
Generality and difficulty in genetic programming: Evolving a sort
– Jr
- 1993
|
|
3
|
On the functional classifier
– Franke
- 1991
|
|
1
|
Zytkow, "Discovery of equations: Experimental evaluation of convergence
– Zembowicz, M
- 1992
|
|
1
|
Teaching neural networks by genetic exploration, " GMD-Arbeitspapiere
– Zhang
- 1993
|
|
