Method of selecting characeteristics data for a data processing system
First Claim
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.
2 Assignments
0 Petitions
Accused Products
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.
11 Citations
1 Claim
-
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.
-
Specification