Please use this identifier to cite or link to this item:
http://hdl.handle.net/1942/39031
Full metadata record
DC Field | Value | Language |
---|---|---|
dc.contributor.author | NAPOLES RUIZ, Gonzalo | - |
dc.contributor.author | Grau, I. | - |
dc.contributor.author | CONCEPCION PEREZ, Leonardo | - |
dc.contributor.author | Salgueiro, Yamisleydi | - |
dc.date.accessioned | 2022-12-14T14:45:59Z | - |
dc.date.available | 2022-12-14T14:45:59Z | - |
dc.date.issued | 2021 | - |
dc.date.submitted | 2022-12-06T14:19:37Z | - |
dc.identifier.citation | Proceedings of the 11th International Conference on Pattern Recognition Systems, Institution of Engineering and Technology, p. 25 -30 | - |
dc.identifier.isbn | 978-1-83953-430-0 | - |
dc.identifier.uri | http://hdl.handle.net/1942/39031 | - |
dc.description.abstract | Long-term Cognitive Networks (LTCNs) are recurrent neural networks for modeling and simulation. Such networks can be trained in a synaptic or non-synaptic mode according to their goal. Non-synaptic learning refers to adjusting the transfer function parameters while preserving the weights connecting the neurons. In that regard, the Non-synaptic Backpropagation (NSBP) algorithm has proven successful in training LTCN-based models. Despite NSBP’s success, a question worthy of investigation is whether the backpropagation process is necessary when training these recurrent neural networks. This paper investigates this issue and presents three non-synaptic learning methods that modify the original algorithm. In addition, we perform a sensitivity analysis of both the NSBP’s hyperparameters and the LTCNs’ learnable parameters. The main conclusions of our study are i) the backward process attached to the NSBP algorithm is not necessary to train these recurrent neural systems, and ii) there is a non-synaptic learnable parameter that does not contribute significantly to the LTCNs’ performance. | - |
dc.language.iso | en | - |
dc.publisher | Institution of Engineering and Technology | - |
dc.subject.other | NSBP algorithm | - |
dc.subject.other | recurrent neural systems | - |
dc.subject.other | nonsynaptic learnable parameter | - |
dc.subject.other | synaptic mode | - |
dc.subject.other | nonsynaptic mode | - |
dc.subject.other | transfer function parameters | - |
dc.subject.other | nonsynaptic backpropagation algorithm | - |
dc.subject.other | LTCN based models | - |
dc.subject.other | backpropagation process | - |
dc.subject.other | recurrent neural networks | - |
dc.subject.other | nonsynaptic learning | - |
dc.subject.other | hyperparameters | - |
dc.subject.other | long-term cognitive networks | - |
dc.subject.other | learnable parameters | - |
dc.title | On the Performance of the Nonsynaptic Backpropagation for Training Long-term Cognitive Networks | - |
dc.type | Proceedings Paper | - |
local.bibliographicCitation.conferencedate | 17/03/21 → 19/03/21 | - |
local.bibliographicCitation.conferencename | 11th International Conference on Pattern Recognition Systems (ICPRS 2021) | - |
local.bibliographicCitation.conferenceplace | Curico, Chile | - |
dc.identifier.epage | 30 | - |
dc.identifier.spage | 25 | - |
local.format.pages | 6 | - |
local.bibliographicCitation.jcat | C1 | - |
local.type.refereed | Refereed | - |
local.type.specified | Proceedings Paper | - |
dc.identifier.doi | 10.1049/icp.2021.1434 | - |
local.provider.type | CrossRef | - |
local.bibliographicCitation.btitle | Proceedings of the 11th International Conference on Pattern Recognition Systems | - |
local.uhasselt.international | yes | - |
item.fulltext | With Fulltext | - |
item.accessRights | Restricted Access | - |
item.fullcitation | NAPOLES RUIZ, Gonzalo; Grau, I.; CONCEPCION PEREZ, Leonardo & Salgueiro, Yamisleydi (2021) On the Performance of the Nonsynaptic Backpropagation for Training Long-term Cognitive Networks. In: Proceedings of the 11th International Conference on Pattern Recognition Systems, Institution of Engineering and Technology, p. 25 -30. | - |
item.contributor | NAPOLES RUIZ, Gonzalo | - |
item.contributor | Grau, I. | - |
item.contributor | CONCEPCION PEREZ, Leonardo | - |
item.contributor | Salgueiro, Yamisleydi | - |
Appears in Collections: | Research publications |
Files in This Item:
File | Description | Size | Format | |
---|---|---|---|---|
On_the_Performance_of_the_Nonsynaptic_Backpropagation_for_Training_Long-term_Cognitive_Networks.pdf Restricted Access | Published version | 164.02 kB | Adobe PDF | View/Open Request a copy |
Page view(s)
46
checked on Aug 6, 2023
Download(s)
10
checked on Aug 6, 2023
Google ScholarTM
Check
Altmetric
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.