HIERARCHICAL NEURAL NETWORK AND ITS LEARNING METHOD

Japanese Patent JP3273568

B2

PURPOSE: To speedily execute learning by providing a second correction means correcting respective connection weights to the correction value of the prescribed number of connection weights, which are calculated in a third calculation means, for a hierarchical neural network.
CONSTITUTION: One connection weight in plural neuron elements is test-corrected in at least one direction between positive and negative directions by prescribed test width S in a first correction means. The first and second calculation means respectively calculate square errors before and after test correction for the input of the same learning pattern. A direction decision means decides the positive or negative direction of test correction width, in which the square error becomes smaller than that before test correction, and the third calculation means calculates the correction value of the connection weight. Then, the second correction means calculates the prescribed number of connection weights and the connection weight is corrected to the correction value obtained by calculating the prescribed number of connection weights in the second correction means. Thus, the fluctuation of the output error in a neuron element network, which occurs in the single test correction of respective connection weights, is checked and the correction direction and the correction value of the connection weight are decided. Thus, only little calculation amount is required.

Norio Akamatsu

JP24838991A

April 08, 2002

September 03, 1991

Click for automatic bibliography generation  

Just System Co., Ltd.

G06F15/18; G06G7/60; G06N3/08; G06N99/00; (IPC1-7): G06N3/08

JP3226884A

Takashi Kawai (1 person outside)

Previous Patent: SIGNAL RECORDING AND REPRODUCING DEVICE AND SIGNAL RECORDING MEDIUM

Next Patent: LITHIUM CELL