Please use this identifier to cite or link to this item:
http://hdl.handle.net/1942/29770
Full metadata record
DC Field | Value | Language |
---|---|---|
dc.contributor.author | NAPOLES RUIZ, Gonzalo | - |
dc.contributor.author | VANHOENSHOVEN, Frank | - |
dc.contributor.author | Falcon, Rafael | - |
dc.contributor.author | VANHOOF, Koen | - |
dc.date.accessioned | 2019-10-17T07:43:11Z | - |
dc.date.available | 2019-10-17T07:43:11Z | - |
dc.date.issued | 2020 | - |
dc.identifier.citation | IEEE Transactions on Neural Networks and Learning Systems, 31 (3), p. 865-875 | - |
dc.identifier.issn | 2162-237X | - |
dc.identifier.uri | http://hdl.handle.net/1942/29770 | - |
dc.description.abstract | We introduce a neural cognitive mapping technique named long-term cognitive network (LTCN) that is able to memorize long-term dependencies between a sequence of input and output vectors, especially in those scenarios that require predicting the values of multiple dependent variables at the same time. The proposed technique is an extension of a recently proposed method named short-term cognitive network that aims at preserving the expert knowledge encoded in the weight matrix while optimizing the nonlinear mappings provided by the transfer function of each neuron. A nonsynaptic, backpropagation-based learning algorithm powered by stochastic gradient descent is put forward to iteratively optimize four parameters of the generalized sigmoid transfer function associated with each neuron. Numerical simulations over 35 multivariate regression and pattern completion data sets confirm that the proposed LTCN algorithm attains statistically significant performance differences with respect to other well-known state-of-the-art methods. | - |
dc.language.iso | en | - |
dc.publisher | IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC | - |
dc.rights | 2019 IEEE. Personal use is permitted, but republication/redistribution requires IEEE permission | - |
dc.subject.other | Associative memories | - |
dc.subject.other | cognitive mapping | - |
dc.subject.other | error backpropagation | - |
dc.subject.other | long-term memory | - |
dc.subject.other | nonsynaptic learning | - |
dc.subject.other | recurrent neural networks | - |
dc.title | Nonsynaptic Error Backpropagation in Long-Term Cognitive Networks | - |
dc.type | Journal Contribution | - |
dc.identifier.epage | 875 | - |
dc.identifier.issue | 3 | - |
dc.identifier.spage | 865 | - |
dc.identifier.volume | 31 | - |
local.bibliographicCitation.jcat | A1 | - |
local.publisher.place | 445 HOES LANE, PISCATAWAY, NJ 08855-4141 USA | - |
local.type.refereed | Refereed | - |
local.type.specified | Article | - |
dc.identifier.doi | 10.1109/TNNLS.2019.2910555 | - |
dc.identifier.pmid | 31059456 | - |
dc.identifier.isi | WOS:000521961300013 | - |
dc.identifier.eissn | 2162-2388 | - |
local.provider.type | Web of Science | - |
local.uhasselt.international | yes | - |
item.validation | ecoom 2021 | - |
item.contributor | NAPOLES RUIZ, Gonzalo | - |
item.contributor | VANHOENSHOVEN, Frank | - |
item.contributor | Falcon, Rafael | - |
item.contributor | VANHOOF, Koen | - |
item.accessRights | Restricted Access | - |
item.fullcitation | NAPOLES RUIZ, Gonzalo; VANHOENSHOVEN, Frank; Falcon, Rafael & VANHOOF, Koen (2020) Nonsynaptic Error Backpropagation in Long-Term Cognitive Networks. In: IEEE Transactions on Neural Networks and Learning Systems, 31 (3), p. 865-875. | - |
item.fulltext | With Fulltext | - |
crisitem.journal.issn | 2162-237X | - |
crisitem.journal.eissn | 2162-2388 | - |
Appears in Collections: | Research publications |
Files in This Item:
File | Description | Size | Format | |
---|---|---|---|---|
manuscript.pdf Restricted Access | Peer-reviewed author version | 941.38 kB | Adobe PDF | View/Open Request a copy |
SCOPUSTM
Citations
1
checked on Sep 5, 2020
WEB OF SCIENCETM
Citations
9
checked on Apr 30, 2024
Page view(s)
134
checked on Jul 14, 2022
Download(s)
84
checked on Jul 14, 2022
Google ScholarTM
Check
Altmetric
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.