Title :
Prediction error of stochastic learning machine
Author :
Ikeda, Kazushi ; Murata, Noboru ; Amari, Shun-Ichi
Author_Institution :
Fac. of Eng., Tokyo Univ., Japan
fDate :
27 Jun-2 Jul 1994
Abstract :
The more the number of training examples included, the better a learning machine will behave. It is an important to know how fast and how well the behavior is improved. The average prediction error is one of the most popular criteria to evaluate the behavior. We have regarded the machine learning from the point of view of parameter estimation and derived the average prediction error of stochastic dichotomy machines by the information geometrical method
Keywords :
error statistics; learning by example; learning systems; maximum likelihood estimation; neural nets; parameter estimation; information geometrical method; maximum likelihood estimation; parameter estimation; prediction error; probability distribution; stochastic dichotomy machines; stochastic learning machine; training examples; Machine learning; Parameter estimation; Signal generators; Stochastic processes; Testing; Tiles;
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.1994.374346
