The relation existing between support vector machines (SVMs) and recurrent associative memories is investigated. The design of associative memories based on the generalized brain-state-in-a-box (GBSB) neural model formulated as a set of independent classification tasks, which can be efficiently solved by standard software packages for SVM learning. Some properties of the networks designed in this way are evidenced, like a surprising generalized Hebb's law. The performance of the SVM approach is compared to existing methods with non-symmetric connections, by some design examples.
Casali, D., Costantini, G., Perfetti, R., Ricci, E. (2008). A new Algorithm for Implementing BSB-based Associative Memories. In PROCEEDINGS OF THE 12TH WSEAS INTERNATIONAL CONFERENCE ON CIRCUITS - NEW ASPECTS OF CIRCUITS (pp.147-151). ATHENS : WORLD SCIENTIFIC AND ENGINEERING ACAD AND SOC.
A new Algorithm for Implementing BSB-based Associative Memories
COSTANTINI, GIOVANNI;
2008-01-01
Abstract
The relation existing between support vector machines (SVMs) and recurrent associative memories is investigated. The design of associative memories based on the generalized brain-state-in-a-box (GBSB) neural model formulated as a set of independent classification tasks, which can be efficiently solved by standard software packages for SVM learning. Some properties of the networks designed in this way are evidenced, like a surprising generalized Hebb's law. The performance of the SVM approach is compared to existing methods with non-symmetric connections, by some design examples.I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.
