Next Article in Journal
Asymptotic Normality for Plug-In Estimators of Generalized Shannon’s Entropy
Next Article in Special Issue
Slope Entropy Characterisation: The Role of the δ Parameter
Previous Article in Journal
A Novel Method for Fault Diagnosis of Rotating Machinery
 
 
Font Type:
Arial Georgia Verdana
Font Size:
Aa Aa Aa
Line Spacing:
Column Width:
Background:
Article

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

1
Department of Physics and Astronomy, University of Bologna, 40126 Bologna, Italy
2
Department of Experimental, Diagnostic and Specialty Medicine, University of Bologna, 40126 Bologna, Italy
3
INFN, 40127 Bologna, Italy
4
Department of Science, Bryant University, Smithfield, RI 02917, USA
*
Author to whom correspondence should be addressed.
These authors contributed equally to this work.
Entropy 2022, 24(5), 682; https://doi.org/10.3390/e24050682
Submission received: 10 February 2022 / Revised: 16 March 2022 / Accepted: 9 May 2022 / Published: 12 May 2022

Abstract

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.
Keywords: machine learning; neural networks; optimization; entropy; learning algorithm machine learning; neural networks; optimization; entropy; learning algorithm

Share and Cite

MDPI and ACS Style

Squadrani, L.; Curti, N.; Giampieri, E.; Remondini, D.; Blais, B.; Castellani, G. Effectiveness of Biologically Inspired Neural Network Models in Learning and Patterns Memorization. Entropy 2022, 24, 682. https://doi.org/10.3390/e24050682

AMA Style

Squadrani L, Curti N, Giampieri E, Remondini D, Blais B, Castellani G. Effectiveness of Biologically Inspired Neural Network Models in Learning and Patterns Memorization. Entropy. 2022; 24(5):682. https://doi.org/10.3390/e24050682

Chicago/Turabian Style

Squadrani, Lorenzo, Nico Curti, Enrico Giampieri, Daniel Remondini, Brian Blais, and Gastone Castellani. 2022. "Effectiveness of Biologically Inspired Neural Network Models in Learning and Patterns Memorization" Entropy 24, no. 5: 682. https://doi.org/10.3390/e24050682

APA Style

Squadrani, L., Curti, N., Giampieri, E., Remondini, D., Blais, B., & Castellani, G. (2022). Effectiveness of Biologically Inspired Neural Network Models in Learning and Patterns Memorization. Entropy, 24(5), 682. https://doi.org/10.3390/e24050682

Note that from the first issue of 2016, this journal uses article numbers instead of page numbers. See further details here.

Article Metrics

Back to TopTop