Title :
A method for the design of evolutionary multilayer neural networks
Author :
Sin, Sam-Kit ; DeFigueiredo, Rui J P
Author_Institution :
Dept. of Electr. & Comput. Eng., California Unv., Irvine, CA, USA
Abstract :
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
Keywords :
feedforward neural nets; basis elements; basis selection problem; evolutionary multilayer neural networks; greedy basis selection algorithm; in-depth evolution; in-width evolution; sample I/O pairs; two-layer nets; Design methodology; Function approximation; Iterative methods; Multi-layer neural network; Neural networks; Neurons; Page description languages; Samarium; Silicon compounds; Tin;
Conference_Titel :
Neural Networks, 1993., IEEE International Conference on
Conference_Location :
San Francisco, CA
Print_ISBN :
0-7803-0999-5
DOI :
10.1109/ICNN.1993.298672
