Using a feed-forward network to incorporate the relation between attractees and attractors in a generalized discrete Hopfield network
UNSPECIFIED. (1996) Using a feed-forward network to incorporate the relation between attractees and attractors in a generalized discrete Hopfield network. INTERNATIONAL JOURNAL OF NEURAL SYSTEMS, 7 (3). pp. 273-286. ISSN 0129-0657Full text not available from this repository.
This paper demonstrates how a feedforward network with constant connection matrices may be used to train a Hopfield style network for pattern recognition. The connection matrix of the Hopfield style network is asymmetric and its diagonal is non-zero. The Hopfield style network referred to as a GDHN is trained to incorporate a relation between attractees and attractors. The attractees represent class samples and the attractors represent class prototypes. The feedforward network is trained using a gradient descent method. Gradients are fed forward in the network to obtain a gradient for a cost function.
|Item Type:||Journal Article|
|Subjects:||Q Science > QA Mathematics > QA76 Electronic computers. Computer science. Computer software|
|Journal or Publication Title:||INTERNATIONAL JOURNAL OF NEURAL SYSTEMS|
|Publisher:||WORLD SCIENTIFIC PUBL CO PTE LTD|
|Official Date:||July 1996|
|Number of Pages:||14|
|Page Range:||pp. 273-286|
Actions (login required)