发明名称 |
Method for processing data using a neural network having a number of layers equal to an abstraction degree of the pattern to be processed |
摘要 |
There is provided a layer construction of neural layers according to the abstraction degree of data to be processed, and data is inputted to a neural layer corresponding to its abstraction degree.
|
申请公布号 |
US5553196(A) |
申请公布日期 |
1996.09.03 |
申请号 |
US19950461538 |
申请日期 |
1995.06.05 |
申请人 |
YOZAN, INC.;SHARP CORPORATION |
发明人 |
TAKATORI, SUNAO;KUMAGAI, RYOHEI;MATSUMOTO, KOJI;YAMAMOTO, MAKOTO |
分类号 |
G06K9/48;G06N3/04;G06N3/063;G06T7/00;(IPC1-7):G06F15/18 |
主分类号 |
G06K9/48 |
代理机构 |
|
代理人 |
|
主权项 |
|
地址 |
|