论文信息 - A method for the design of evolutionary multilayer neural networks

A method for the design of evolutionary multilayer neural networks

A method is presented for the design of evolutionary multilayer neural networks. This method supports both in-depth and in-width evolution. The proposed multilayer structure is obtained by cascading several sections of two-layer nets. The construction of each two-layer section is formulated as a basis selection problem. By constraining the basis elements to be selected from the input parts of the given sample I/O pairs, a solution can be obtained by using a greedy basis selection algorithm. Simulation results are included to illustrate the approach.<<ETX>>

Rui J. P. de Figueiredo | Sam-Kit Sin

[1] K. Lang,et al. Learning to tell two spirals apart , 1988 .

[2] Shang-Liang Chen,et al. Orthogonal least squares learning algorithm for radial basis function networks , 1991, IEEE Trans. Neural Networks.

[3] J. D. Powell,et al. Radial basis function approximations to polynomials , 1989 .

[4] Rui J. P. de Figueiredo,et al. An evolution-oriented learning algorithm for the optimal interpolative net , 1992, IEEE Trans. Neural Networks.

[5] Rui J. P. de Figueiredo,et al. Efficient learning procedures for optimal interpolative nets , 1993, Neural Networks.

[6] Christian Lebiere,et al. The Cascade-Correlation Learning Architecture , 1989, NIPS.

[7] R.J.P. deFigueredo. An optimal multilayer neural interpolating (OMNI) net in a generalized Fock space setting , 1992, [Proceedings 1992] IJCNN International Joint Conference on Neural Networks.

[8] R. D. Figueiredo. A generalized Fock space framework for nonlinear system and signal analysis , 1983 .