NEURAL NETWORK OUTPUTTING MEMBERSHIP FUNCTION

Title:

NEURAL NETWORK OUTPUTTING MEMBERSHIP FUNCTION

Document Type and Number:

Japanese Patent JP3296609

Kind Code:

B2

Abstract:

PURPOSE: To make the type of an NN have flexibility and to obtain a membership function by a balanced arrangement, in the NN outputting the membership function.
CONSTITUTION: This neural network(NN) has a cell 2 and a bias cell 1 outputting input signals, plural first intermediate cells 3 to 6 to be connected with the signals of the cells by a prescribed coupling coefficient, plural second cells 7 to 9 to be connected with these intermediate cells by the prescribed coupling coefficient and two output cells 10, 11. An educator signal of a fixed value is impressed via the one side 10 of the output cells.

More Like This:

JP2000298495	SPECIFYING METHOD OF REGRESSION CLASS TREE STRUCTURE FOR VOICE RECOGNITION DEVICE
JPH0581230	LEARNING DEVICE FOR NEURAL NETWORK
JPH0877283	ANALOG NEURAL NETWORK CIRCUIT

Inventors:

Tetsuro Ren
Chinami Tanaka

Application Number:

JP35685792A

Publication Date:

July 02, 2002

Filing Date:

December 22, 1992

Export Citation:

Click for automatic bibliography generation Help

Assignee:

Mikuni Corporation

International Classes:

G06F15/18; G06F9/44; G06G7/12; G06G7/60; G06N7/02; G06N99/00; (IPC1-7): G06G7/60; G06F9/44; G06F15/18; G06G7/12

Domestic Patent References:

JP3111963A

Attorney, Agent or Firm:

Norio Ishii

Previous Patent: SHAPE MEASURING APPARATUS

Next Patent: PUSHBUTTON OPERATION SECTION FOR ELECTRONIC DEVICE