Method of selecting characeteristics data for a data processing system

• US 5,185,816 A
• Filed: 12/13/1990
• Issued: 02/09/1993
• Est. Priority Date: 12/25/1989
• Status: Expired due to Fees

• Current Assignee: Sharp Corporation (Hon Hai Precision Industry Co., Ltd.)
• Original Assignee: YOZAN, Inc.
• Inventors: Matsumoto, Koji, Yamamoto, Makoto, Takatori, Sunao, Kumagai, Ryohei
• Primary Examiner(s): Mancuso, Joseph
• Assistant Examiner(s): KELLEY, CHRISTOPHER S
• Application Number:
  US07/627,208
• Time in Patent Office: 789 Days
• Field of Search: 382/14, 382/15, 382/56, 382/34, 395/20, 395/21, 395/22, 395/23
• US Class Current: 382/160
• CPC Class Codes: G06F 18/211 Selection of the most significant subset of features
• CPC Class Codes: G06N 3/02 Neural networks
• CPC Class Codes: G06V 30/19167 Active pattern learning

Abstract

A method of selecting characteristics data for a data processing system from a group of input data for reducing data volume of each input data by said data processing system having a neural network structure or a structure equivalent thereto, where each input data consists of a plurality of said characteristics data. The method includes the steps of storing outputs of said input data; selecting a specific characteristics data of a pair of different input data; exchanging said characteristics data of said input data pair with each other; comparing outputs from said data processing system in response to said input data before and after the exchange of said characteristics data; and removing said characteristics data from said input data in said group, when a difference between said outputs before and after is comparatively small.

Claims

1. A method of selecting characteristics data from a group of input data for reducing data volume of each input data of said group, using a data processing system having a neural network structure, where each of said input data includes a plurality of said characteristics data, said method comprising the steps of:

storing an ignition pattern representing neurons corresponding to each of said input data;

selecting one of said characteristics data for a pair of different input data;

exchanging said characteristics data of each input data in said input data pair with each other;

comparing ignition patterns representing neurons corresponding to said input data pair before and after said exchange of said characteristics data; and

removing said characteristics data from said group of input data when a difference between a result from said comparing step is relatively small.