Cargando…

Effectiveness of Biologically Inspired Neural Network Models in Learning and Patterns Memorization

Purpose: In this work, we propose an implementation of the Bienenstock–Cooper–Munro (BCM) model, obtained by a combination of the classical framework and modern deep learning methodologies. The BCM model remains one of the most promising approaches to modeling the synaptic plasticity of neurons, but...

Descripción completa

Detalles Bibliográficos
Autores principales: Squadrani, Lorenzo, Curti, Nico, Giampieri, Enrico, Remondini, Daniel, Blais, Brian, Castellani, Gastone
Formato: Online Artículo Texto
Lenguaje:English
Publicado: MDPI 2022
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9141587/
https://www.ncbi.nlm.nih.gov/pubmed/35626566
http://dx.doi.org/10.3390/e24050682
_version_ 1784715381190950912
author Squadrani, Lorenzo
Curti, Nico
Giampieri, Enrico
Remondini, Daniel
Blais, Brian
Castellani, Gastone
author_facet Squadrani, Lorenzo
Curti, Nico
Giampieri, Enrico
Remondini, Daniel
Blais, Brian
Castellani, Gastone
author_sort Squadrani, Lorenzo
collection PubMed
description Purpose: In this work, we propose an implementation of the Bienenstock–Cooper–Munro (BCM) model, obtained by a combination of the classical framework and modern deep learning methodologies. The BCM model remains one of the most promising approaches to modeling the synaptic plasticity of neurons, but its application has remained mainly confined to neuroscience simulations and few applications in data science. Methods: To improve the convergence efficiency of the BCM model, we combine the original plasticity rule with the optimization tools of modern deep learning. By numerical simulation on standard benchmark datasets, we prove the efficiency of the BCM model in learning, memorization capacity, and feature extraction. Results: In all the numerical simulations, the visualization of neuronal synaptic weights confirms the memorization of human-interpretable subsets of patterns. We numerically prove that the selectivity obtained by BCM neurons is indicative of an internal feature extraction procedure, useful for patterns clustering and classification. The introduction of competitiveness between neurons in the same BCM network allows the network to modulate the memorization capacity of the model and the consequent model selectivity. Conclusions: The proposed improvements make the BCM model a suitable alternative to standard machine learning techniques for both feature selection and classification tasks.
format Online
Article
Text
id pubmed-9141587
institution National Center for Biotechnology Information
language English
publishDate 2022
publisher MDPI
record_format MEDLINE/PubMed
spelling pubmed-91415872022-05-28 Effectiveness of Biologically Inspired Neural Network Models in Learning and Patterns Memorization Squadrani, Lorenzo Curti, Nico Giampieri, Enrico Remondini, Daniel Blais, Brian Castellani, Gastone Entropy (Basel) Article Purpose: In this work, we propose an implementation of the Bienenstock–Cooper–Munro (BCM) model, obtained by a combination of the classical framework and modern deep learning methodologies. The BCM model remains one of the most promising approaches to modeling the synaptic plasticity of neurons, but its application has remained mainly confined to neuroscience simulations and few applications in data science. Methods: To improve the convergence efficiency of the BCM model, we combine the original plasticity rule with the optimization tools of modern deep learning. By numerical simulation on standard benchmark datasets, we prove the efficiency of the BCM model in learning, memorization capacity, and feature extraction. Results: In all the numerical simulations, the visualization of neuronal synaptic weights confirms the memorization of human-interpretable subsets of patterns. We numerically prove that the selectivity obtained by BCM neurons is indicative of an internal feature extraction procedure, useful for patterns clustering and classification. The introduction of competitiveness between neurons in the same BCM network allows the network to modulate the memorization capacity of the model and the consequent model selectivity. Conclusions: The proposed improvements make the BCM model a suitable alternative to standard machine learning techniques for both feature selection and classification tasks. MDPI 2022-05-12 /pmc/articles/PMC9141587/ /pubmed/35626566 http://dx.doi.org/10.3390/e24050682 Text en © 2022 by the authors. https://creativecommons.org/licenses/by/4.0/Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/).
spellingShingle Article
Squadrani, Lorenzo
Curti, Nico
Giampieri, Enrico
Remondini, Daniel
Blais, Brian
Castellani, Gastone
Effectiveness of Biologically Inspired Neural Network Models in Learning and Patterns Memorization
title Effectiveness of Biologically Inspired Neural Network Models in Learning and Patterns Memorization
title_full Effectiveness of Biologically Inspired Neural Network Models in Learning and Patterns Memorization
title_fullStr Effectiveness of Biologically Inspired Neural Network Models in Learning and Patterns Memorization
title_full_unstemmed Effectiveness of Biologically Inspired Neural Network Models in Learning and Patterns Memorization
title_short Effectiveness of Biologically Inspired Neural Network Models in Learning and Patterns Memorization
title_sort effectiveness of biologically inspired neural network models in learning and patterns memorization
topic Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9141587/
https://www.ncbi.nlm.nih.gov/pubmed/35626566
http://dx.doi.org/10.3390/e24050682
work_keys_str_mv AT squadranilorenzo effectivenessofbiologicallyinspiredneuralnetworkmodelsinlearningandpatternsmemorization
AT curtinico effectivenessofbiologicallyinspiredneuralnetworkmodelsinlearningandpatternsmemorization
AT giampierienrico effectivenessofbiologicallyinspiredneuralnetworkmodelsinlearningandpatternsmemorization
AT remondinidaniel effectivenessofbiologicallyinspiredneuralnetworkmodelsinlearningandpatternsmemorization
AT blaisbrian effectivenessofbiologicallyinspiredneuralnetworkmodelsinlearningandpatternsmemorization
AT castellanigastone effectivenessofbiologicallyinspiredneuralnetworkmodelsinlearningandpatternsmemorization