An SVM based method for associative memories

Authors:
Daniele Casali;Giovanni Costantini;Massimiliano Todisco
Affiliations:
Department of Electronic Engineering, University of Rome "Tor Vergata", Italy;Department of Electronic Engineering, University of Rome "Tor Vergata", Italy;Department of Electronic Engineering, University of Rome "Tor Vergata", Italy
Venue:
ICCOMP'10 Proceedings of the 14th WSEAS international conference on Computers: part of the 14th WSEAS CSCC multiconference - Volume II
Year:
2010

Citing 6
Cited 0

Introduction to artificial neural systems

Introduction to artificial neural systems
Making large-scale support vector machine learning practical

Advances in kernel methods
A Tutorial on Support Vector Machines for Pattern Recognition

Data Mining and Knowledge Discovery
On neural networks that design neural associative memories

IEEE Transactions on Neural Networks
A new synthesis approach for feedback neural networks based on the perceptron training algorithm

IEEE Transactions on Neural Networks
A synthesis procedure for brain-state-in-a-box neural networks

IEEE Transactions on Neural Networks

Quantified Score

Hi-index	0.00

Visualization

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 is 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.