Download:
by Byoung-tak Zhang, Heinz Muhlenbein
Proceedings of the 5th international conference on genetic algorithms (ICGA'93
http://www.geocities.com/francorbusetti/Occamnns.pdf
Add To MetaCart
Abstract:
A genetic programming method is investigated for optimizing both the architecture and the connection weights of multilayer feedforward neural networks. The genotype of each network is represented as a tree whose depth and width are dynamically adapted to the particular application by speci cally de ned genetic operators. The weights are trained by a next-ascent hillclimbing search. A new tness function is proposed that quanti es the principle of Occam's razor. It makes an optimal trade-o between the error tting ability and the parsimony ofthenetwork. We discuss the results for two problems of di ering complexity and study the convergence and scaling properties of the algorithm. 1
Citations
|
2140
|
Learning Internal Representations by Error Propagation
– Rumelhart, Hinton, et al.
- 1986
|
|
524
|
Networks for approximation and learning
– Poggio, Girosi
- 1990
|
|
417
|
A logical calculus of the ideas immanent in nervous activity
– McCulloch, Pitts
- 1943
|
|
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
|
|
185
|
Designing neural networks using genetic algorithms
– F, Todd, et al.
- 1989
|
|
117
|
Bayesian Methods for Adaptive Models
– MacKay
- 1992
|
|
103
|
Genetic Programming: A Paradigm for Genetically Breeding Populations of Computer Programs to Solve Problems
– Koza
- 1990
|
|
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
|
|
42
|
Genetic synthesis of Boolean neural networks with a cell rewriting developmental process
– Gruau
- 1992
|
|
38
|
Consistent inference of probabilities in layered networks: predictions and generalization
– Tishby, Levin, et al.
- 1989
|
|
36
|
The Vapnik-Chervonenkis dimension: Information versus complexity in learning
– Abu-Mostafa
- 1989
|
|
32
|
Polynomial theory of complex systems
– Ivakhnenko
- 1971
|
|
15
|
Evolutionary algorithms: theory and applications
– Mühlenbein
- 1993
|
|
7
|
A quantitative Occam's razor
– Sorkin
- 1983
|
|
7
|
Focused incremental learning for improved generalization with reduced training sets
– Zhang, Veenker
- 1991
|
|
4
|
The dynamics of evolution and learning---Towards genetic neural networks
– Muhlenbein, Kindermann
- 1989
|
|
1
|
Learning by Genetic Neural Evolution. (in German), Sankt Augustin
– Zhang
- 1992
|