Michael Jones
- 1.ACKLEY, D., AND LITMAN, N{. Interactions bethe Second Conference on Artificial Life (Reading, MA, 1991), Addison-Wesley, pp. 487-509.Google Scholar
- 2.BALDWIN, J. Development and Evolution: {n- Orthoplasy and Theory of Genetics. AMS Press, Nh~v. Vr~rlt NlV 1(10(1Google Scholar
- 3.FOGEL, D. Evolutionary Computation. IEEE Press, New York, NY, 1995. Google ScholarDigital Library
- 4.HAGEN, M. DEMUTH, H., AND BEALUE M. Neural Network Design. PWS, Boston, MA, 1995.Google Scholar
- 5.HINTON, G. E., AND NOLWAN, S. J. How learning can guide evolution. Complex Systems / (1987), 495-502.Google Scholar
- 6.KOHONEN, T. Self-Organizing Maps. Springer- Verlag, Herlin, Germany, 1995. Google ScholarDigital Library
- 7.LEVY, S. Artificial Life: A Quest for New Creation. Pantheon Books, New York, NY, 1992. Google ScholarDigital Library
- 8.MTTCHELL, M. introduction to Genetic Aigorithms. MIT Press, Cambridge, MA, 1996. Google ScholarDigital Library
- 9.RAO, V., AND RAO, H. C-t-+ Neural Networks and F~,.zzy Logic. IDG Rooks, Foster City, CA, 1995. Google ScholarDigital Library
- 10.SANTAMARIA, J., AND SUTTON, R. A standard interface for reinforcement learning, 1996. {http'//envy. cs.umass.edu/.-,rich/RLinterface / RLinterface.html}.Google Scholar
- 11.WALL, M. Galib, a collection of genotir' nrncrrnmmln ar Pnrn nAnont'. {http'//lancet.mit.edu}Google Scholar
- 12.WHITLEY, D., GORDON, V. S., AND MATHIAS, K. Lamarckian evolution, the baldwin effect and function optimization. In Parallel Problem Solving from Nature-PPSN III. (1994), Y. Davidor, H. Schwefel, and R. Manner, Eds., no. 866 in Lecture Notes in Computer Science, pp. 6-15. Google ScholarDigital Library
Index Terms
- The use of genetic algorithms and neural networks to investigate the Baldwin effect
Recommendations
Neural network crossover in genetic algorithms using genetic programming
AbstractThe use of genetic algorithms (GAs) to evolve neural network (NN) weights has risen in popularity in recent years, particularly when used together with gradient descent as a mutation operator. However, crossover operators are often omitted from ...
Biological engineering applications of feedforward neural networks designed and parameterized by genetic algorithms
Two neural network (NN) applications in the field of biological engineering are developed, designed and parameterized by an evolutionary method based on the evolutionary process of genetic algorithms. The developed systems are a fault detection NN model ...
A hybrid genetic algorithm with the Baldwin effect
Here we present a new hybrid genetic algorithm (HGA) with the Baldwin effect. In the HGA, a local search is employed to change the fitness of individuals but the acquired improvements do not change the individual itself. This local search step exploits ...
Comments