On the Performance of the Nonsynaptic Backpropagation for Training Long-term Cognitive Networks

Gonzalo Nápoles, Isel Grau, Leonardo Concepcion, Yamisleydi Salgueiro

Research output: Chapter in Book/Report/Conference proceedingConference paper

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.
Original languageEnglish
Title of host publicationProceedings of the 11th International Conference on Pattern Recognition Systems
Pages1-6
Number of pages6
Publication statusAccepted/In press - 2021
Event11th International Conference on Pattern Recognition Systems - Curico, Chile
Duration: 17 Mar 202119 Mar 2021
http://www.icprs.org/

Conference

Conference11th International Conference on Pattern Recognition Systems
Abbreviated titleICPRS 2021
CountryChile
CityCurico
Period17/03/2119/03/21
Internet address

Fingerprint Dive into the research topics of 'On the Performance of the Nonsynaptic Backpropagation for Training Long-term Cognitive Networks'. Together they form a unique fingerprint.

Cite this