论文信息 - Determination of the topology and weights of the feedforward ANN by genetic evolution

Determination of the topology and weights of the feedforward ANN by genetic evolution

This paper proposes an evolutionary based method to design the feedforward Artificial Neural Networks (ANN). The Evolutionary Programming method evolves concurrently the topology and weight distribution of ANN, accelerates the rate of convergence of the solution obtained, and approaches the global optimal solution, then BP is used to train the exact weight values. The experiments demonstrate the method is promising.

Jie-Gu Li | Xiaodong Tang

[1] Donald E. Waagen,et al. Evolving recurrent perceptrons for time-series modeling , 1994, IEEE Trans. Neural Networks.

[2] Stephen A. Billings,et al. Radial basis function network configuration using genetic algorithms , 1995, Neural Networks.

[3] David B. Fogel,et al. An introduction to simulated evolutionary optimization , 1994, IEEE Trans. Neural Networks.

[4] Vittorio Maniezzo,et al. Genetic evolution of the topology and weight distribution of neural networks , 1994, IEEE Trans. Neural Networks.

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