Conference Proceeding

High capacity content addressable memory with mixed order hyper networks

Details

Citation

Swingler K (2017) High capacity content addressable memory with mixed order hyper networks. In: Merelo J, Rosa A, Cadenas J, Correia A, Mandani K, Ruano A & Filipe J (eds.) Computational Intelligence: International Joint Conference, IJCCI 2015 Lisbon, Portugal, November 12-14, 2015, Revised Selected Papers. Studies in Computational Intelligence, 669. Computational Intelligence International Joint Conference, IJCCI 2015, Lisbon, Portugal, 12.11.2015-14.11.2015. Cham, Switzerland: Springer, pp. 337-358. https://doi.org/10.1007/978-3-319-48506-5_17

Abstract
A mixed order hyper network (MOHN) is a neural network in which weights can connect any number of neurons, rather than the usual two. MOHNs can be used as content addressable memories (CAMs) with higher capacity than standard Hopfield networks. They can also be used for regression learning of functions in ƒ : {−1,1}n→R in which the turning points are equivalent to memories in a CAM. This paper presents a number of methods for learning an energy function from data that can act as either a CAM or a regression model and presents the advantages of using such an approach.

StatusPublished
Title of seriesStudies in Computational Intelligence
Number in series669
Publication date31/12/2017
Publication date online30/11/2015
URLhttp://hdl.handle.net/1893/26263
PublisherSpringer
Place of publicationCham, Switzerland
ISSN of series1860-949X
ISBN978-3-319-48504-1
eISBN978-3-319-48506-5
ConferenceComputational Intelligence International Joint Conference, IJCCI 2015
Conference locationLisbon, Portugal
Dates

People (1)

People

Professor Kevin Swingler

Professor Kevin Swingler

Professor, Computing Science