Title :
A learning machine that evolves
Author :
Nakano, Kaoru ; Hiraki, Hideaki ; Ikeda, Shiro
Author_Institution :
Dept. of Math. Eng. & Inf. Phys., Tokyo Univ., Japan
fDate :
29 Nov-1 Dec 1995
Abstract :
We propose a simple model of a learning machine that evolves. When a classification problem is given, a perceptron like learning machine obtains a proper set of feature detecting cells through mating, mutation, and natural selection. Computer simulation showed the expected results. This is one of our trials to approach the evolutionary system in the real world
Keywords :
feature extraction; genetic algorithms; learning (artificial intelligence); pattern classification; perceptrons; classification problem; computer simulation; evolutionary system; feature detecting cells; mating; mutation; natural selection; perceptron like learning machine; real world; Backpropagation; Computer simulation; Computer vision; Evolutionary computation; Feature extraction; Genetic mutations; Machine learning; Physics; Robotics and automation; Robots;
Conference_Titel :
Evolutionary Computation, 1995., IEEE International Conference on
Conference_Location :
Perth, WA
Print_ISBN :
0-7803-2759-4
DOI :
10.1109/ICEC.1995.487490