Published 1988
| Published
Book Section - Chapter
Open
Learning on a General Network
- Creators
- Atiya, Amir F.
- Other:
- Anderson, Dana Z.
Abstract
This paper generalizes the back-propagation method to a general network containing feedback connections. The network model considered consists of interconnected groups of neurons, where each group could be fully interconnected (it could have feedback connections, with possibly asymmetric weights), but no loops between the groups are allowed. A stochastic descent algorithm is applied, under a certain inequality constraint on each intra-group weight matrix which ensures for the network to possess a unique equilibrium state for every input.
Additional Information
© American Institute of Physics 1988.Attached Files
Published - 9-learning-on-a-general-network.pdf
Files
9-learning-on-a-general-network.pdf
Files
(1.4 MB)
Name | Size | Download all |
---|---|---|
md5:b903155064e6bcd4e541aeac8a0a7779
|
1.4 MB | Preview Download |
Additional details
- Eprint ID
- 63459
- Resolver ID
- CaltechAUTHORS:20160107-153055194
- Created
-
2016-01-19Created from EPrint's datestamp field
- Updated
-
2019-10-03Created from EPrint's last_modified field