Title :
Penalized learning as multiple object optimization
Author :
Matsuyama, Yasuo ; Nakayama, Haruo ; Sasai, Taketoshi ; Chen, Yuh Perng
Author_Institution :
Dept. of Comput. & Inf. Sci., Ibaraki Univ., Japan
fDate :
27 Jun-2 Jul 1994
Abstract :
Learning algorithms guided by costs with a variety of penalties are discussed. Both unsupervised and supervised cases are addressed. The penalties are added and/or multiplied to the basic error measure. Since these extra penalties include combination parameters with respect to the basic error, the total problem belongs to a class of multiple object optimization. Learning algorithms in general cases are derived first. Then, individual cases such as penalties on undesirable weights and outputs are treated. A method to find a preferred solution among the Pareto optimal set of the multiple object optimization is given
Keywords :
learning (artificial intelligence); neural nets; optimisation; Pareto optimal set; error measure; multiple object optimization; neural nets; penalized learning; supervised learning; unsupervised learning; Additives; Backpropagation; Computer errors; Concrete; Cost function; Error correction; Pareto optimization; Vector quantization;
Conference_Titel :
Neural Networks, 1994. IEEE World Congress on Computational Intelligence., 1994 IEEE International Conference on
Conference_Location :
Orlando, FL
Print_ISBN :
0-7803-1901-X
DOI :
10.1109/ICNN.1994.374160
