发明名称 |
Neural network learning system for inferring an input-output relationship from a set of given input and output samples |
摘要 |
A neural network learning system in which an input-output relationship is inferred. The system includes a probability density part for determining a probability density on a sum space of an input space and an output space from a set of given input and output samples by learning, the probability density on the sum space being defined to have a parameter, and an inference part for inferring a probability density function based on the probability density from the probability density part, so that an input-output relationship of the samples is inferred from the probability density function having a parameter value determined by learning, the learning of the parameter being repeated until the value of a predefined parameter differential function using a prescribed maximum likelihood method is smaller than a prescribed reference value.
|
申请公布号 |
US5479576(A) |
申请公布日期 |
1995.12.26 |
申请号 |
US19950393024 |
申请日期 |
1995.02.23 |
申请人 |
RICOH COMPANY, LTD. |
发明人 |
WATANABE, SUMIO;FUKUMIZU, KENJI |
分类号 |
G06F15/18;G06G7/60;G06N3/04;G06N3/08;G06N99/00;(IPC1-7):G06F15/18 |
主分类号 |
G06F15/18 |
代理机构 |
|
代理人 |
|
主权项 |
|
地址 |
|