论文信息 - Evolving recurrent neural networks with non-binary encoding

Evolving recurrent neural networks with non-binary encoding

This paper presents an evolutionary approach for the design of feedforward and recurrent neural networks. We show that evolutionary algorithms can be used for the construction of networks for real-world tasks. Therefore, a data structure based genotypic network representation, as well as genetic operators, are introduced. Results from the classification, function approximation and time-series domains are presented.

M. Mandischer

[1] Vasant Honavar,et al. Evolutionary Design of Neural Architectures -- A Preliminary Taxonomy and Guide to Literature , 1995 .

[2] Tariq Samad,et al. Designing Application-Specific Neural Networks Using the Genetic Algorithm , 1989, NIPS.

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

[4] Eric A. Wan,et al. Time series prediction by using a connectionist network with internal delay lines , 1993 .

[5] Peter M. Todd,et al. Designing Neural Networks using Genetic Algorithms , 1989, ICGA.

[6] Andreas S. Weigend,et al. Time Series Prediction: Forecasting the Future and Understanding the Past , 1994 .

[7] J. Stephen Judd,et al. Neural network design and the complexity of learning , 1990, Neural network modeling and connectionism.

[8] James E. Baker,et al. Reducing Bias and Inefficienry in the Selection Algorithm , 1987, ICGA.

[9] Martin Mandischer,et al. Representation and Evolution of Neural Networks , 1993 .