An Improvement of Neural Networks Applied to Pharmaceutical Problems.
Bibliographic Information
- Other Title
-
- Improvement of Neural Networks Applied
Search this article
Abstract
In applying the neural network to the classification problem in pharmacology, we adopt an extended back-propagation (EBP) learning which adjusts the parameters appearing in an activation function, as well as the weights. The results of simulations show that such an extended learning speeds up the learning process as compared with the conventional basic back-propagation procedure, irrespective of the initial values of the parameters, which is extremely useful in the practical application of the neural network in the pharmaceutical field. We have also found that use of Morita's activation function beyond the sigmoid type further accelerates the EBP learning in some cases.
Journal
-
- Chemical and Pharmaceutical Bulletin
-
Chemical and Pharmaceutical Bulletin 45 (1), 107-115, 1997
The Pharmaceutical Society of Japan
- Tweet
Keywords
Details 詳細情報について
-
- CRID
- 1390282679139027584
-
- NII Article ID
- 130003947168
- 110003616376
-
- NII Book ID
- AA00602100
-
- COI
- 1:CAS:528:DyaK2sXotFSltg%3D%3D
-
- ISSN
- 13475223
- 00092363
- http://id.crossref.org/issn/00092363
-
- NDL BIB ID
- 4121829
-
- PubMed
- 9023972
-
- Text Lang
- en
-
- Data Source
-
- JaLC
- NDL
- Crossref
- PubMed
- CiNii Articles
-
- Abstract License Flag
- Disallowed