An associative memory for the on-line recognition and prediction of temporal sequences

dc.creatorBose, J.
dc.creatorFurber, S. B.
dc.creatorShapiro, J. L.
dc.date2006-11-05
dc.date.accessioned2026-07-07T07:31:39Z
dc.date.available2026-07-07T07:31:39Z
dc.descriptionThis paper presents the design of an associative memory with feedback that is capable of on-line temporal sequence learning. A framework for on-line sequence learning has been proposed, and different sequence learning models have been analysed according to this framework. The network model is an associative memory with a separate store for the sequence context of a symbol. A sparse distributed memory is used to gain scalability. The context store combines the functionality of a neural layer with a shift register. The sensitivity of the machine to the sequence context is controllable, resulting in different characteristic behaviours. The model can store and predict on-line sequences of various types and length. Numerical simulations on the model have been carried out to determine its properties.
dc.descriptionPublished in IJCNN 2005, Montreal, Canada
dc.identifierhttps://arxiv.org/abs/cs/0611020
dc.identifierhttp://arxiv.org/abs/cs/0611020
dc.identifierdoi:10.1109/IJCNN.2005.1556028
dc.identifier.urihttp://salesiana.dossiersoluciones.com/handle/123456789/118828
dc.subjectNeural and Evolutionary Computing
dc.subjectArtificial Intelligence
dc.titleAn associative memory for the on-line recognition and prediction of temporal sequences
dc.typetext

Files

Collections