dc.contributor.author | Main, Linda | |
dc.contributor.author | Thornton, John | |
dc.date.accessioned | 2018-06-20T23:20:30Z | |
dc.date.available | 2018-06-20T23:20:30Z | |
dc.date.issued | 2017 | |
dc.identifier.doi | 10.1109/SSCI.2017.8285217 | |
dc.identifier.uri | http://hdl.handle.net/10072/377284 | |
dc.description.abstract | Abstract:
Hierarchical Predictive Coding systems that have adopted prediction as their primary goal, are heavily reliant on the stable sparse coding of sensory input. Furthermore, such systems will require their spatial coding function to be adaptive and able to reform to reflect changes within the environment. These properties of stability and adaptiveness should emerge naturally from the spatial coding system and not be reliant on additional control mechanisms. Hierarchical Temporal Memory is a cortically inspired model that encapsulates both sparse coding and temporal processing functions. We present an investigation into the stability and adaptiveness of three alternative versions of the spatial pooling function. Our results show that two of these SP algorithms are able to form stable sparse distributed representations of audio input, while still remaining adaptive to changes within the input data. | |
dc.description.peerreviewed | Yes | |
dc.language | English | |
dc.publisher | Institute of Electrical and Electronics Engineers (IEEE) | |
dc.publisher.place | United States | |
dc.relation.ispartofconferencename | SSCI 2017 | |
dc.relation.ispartofconferencetitle | 2017 IEEE Symposium Series on Computational Intelligence (SSCI 2017) | |
dc.relation.ispartofdatefrom | 2017-11-27 | |
dc.relation.ispartofdateto | 2017-12-01 | |
dc.relation.ispartoflocation | Honolulu, Hawaii, United States | |
dc.subject.fieldofresearch | Artificial Intelligence and Image Processing not elsewhere classified | |
dc.subject.fieldofresearchcode | 080199 | |
dc.title | Stable sparse encoding for predictive processing | |
dc.type | Conference output | |
dc.type.description | E1 - Conferences | |
dc.type.code | E - Conference Publications | |
dc.description.version | Accepted Manuscript (AM) | |
gro.faculty | Griffith Sciences, School of Information and Communication Technology | |
gro.rights.copyright | © 2017 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works. | |
gro.hasfulltext | Full Text | |
gro.griffith.author | Thornton, John R. | |
gro.griffith.author | Main, Linda M. | |