Brain-Inspired Self-Organization with Cellular Neuromorphic Computing for Multimodal Unsupervised Learning
Cortical plasticity is one of the main features that enable our ability to learn and adapt in our environment. Indeed, the cerebral cortex self-organizes itself through structural and synaptic plasticity mechanisms that are very likely at the basis of an extremely interesting characteristic of the h...
Main Authors: | , , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2020-10-01
|
Series: | Electronics |
Subjects: | |
Online Access: | https://www.mdpi.com/2079-9292/9/10/1605 |
_version_ | 1797552111059206144 |
---|---|
author | Lyes Khacef Laurent Rodriguez Benoît Miramond |
author_facet | Lyes Khacef Laurent Rodriguez Benoît Miramond |
author_sort | Lyes Khacef |
collection | DOAJ |
description | Cortical plasticity is one of the main features that enable our ability to learn and adapt in our environment. Indeed, the cerebral cortex self-organizes itself through structural and synaptic plasticity mechanisms that are very likely at the basis of an extremely interesting characteristic of the human brain development: the multimodal association. In spite of the diversity of the sensory modalities, like sight, sound and touch, the brain arrives at the same concepts (convergence). Moreover, biological observations show that one modality can activate the internal representation of another modality when both are correlated (divergence). In this work, we propose the Reentrant Self-Organizing Map (ReSOM), a brain-inspired neural system based on the reentry theory using Self-Organizing Maps and Hebbian-like learning. We propose and compare different computational methods for unsupervised learning and inference, then quantify the gain of the ReSOM in a multimodal classification task. The divergence mechanism is used to label one modality based on the other, while the convergence mechanism is used to improve the overall accuracy of the system. We perform our experiments on a constructed written/spoken digits database and a Dynamic Vision Sensor (DVS)/EletroMyoGraphy (EMG) hand gestures database. The proposed model is implemented on a cellular neuromorphic architecture that enables distributed computing with local connectivity. We show the gain of the so-called hardware plasticity induced by the ReSOM, where the system’s topology is not fixed by the user but learned along the system’s experience through self-organization. |
first_indexed | 2024-03-10T15:55:19Z |
format | Article |
id | doaj.art-cda9d52d57ae4666acbd424b64d469bb |
institution | Directory Open Access Journal |
issn | 2079-9292 |
language | English |
last_indexed | 2024-03-10T15:55:19Z |
publishDate | 2020-10-01 |
publisher | MDPI AG |
record_format | Article |
series | Electronics |
spelling | doaj.art-cda9d52d57ae4666acbd424b64d469bb2023-11-20T15:45:24ZengMDPI AGElectronics2079-92922020-10-01910160510.3390/electronics9101605Brain-Inspired Self-Organization with Cellular Neuromorphic Computing for Multimodal Unsupervised LearningLyes Khacef0Laurent Rodriguez1Benoît Miramond2Université Côte d’Azur, CNRS, LEAT, 06903 Sophia Antipolis, FranceUniversité Côte d’Azur, CNRS, LEAT, 06903 Sophia Antipolis, FranceUniversité Côte d’Azur, CNRS, LEAT, 06903 Sophia Antipolis, FranceCortical plasticity is one of the main features that enable our ability to learn and adapt in our environment. Indeed, the cerebral cortex self-organizes itself through structural and synaptic plasticity mechanisms that are very likely at the basis of an extremely interesting characteristic of the human brain development: the multimodal association. In spite of the diversity of the sensory modalities, like sight, sound and touch, the brain arrives at the same concepts (convergence). Moreover, biological observations show that one modality can activate the internal representation of another modality when both are correlated (divergence). In this work, we propose the Reentrant Self-Organizing Map (ReSOM), a brain-inspired neural system based on the reentry theory using Self-Organizing Maps and Hebbian-like learning. We propose and compare different computational methods for unsupervised learning and inference, then quantify the gain of the ReSOM in a multimodal classification task. The divergence mechanism is used to label one modality based on the other, while the convergence mechanism is used to improve the overall accuracy of the system. We perform our experiments on a constructed written/spoken digits database and a Dynamic Vision Sensor (DVS)/EletroMyoGraphy (EMG) hand gestures database. The proposed model is implemented on a cellular neuromorphic architecture that enables distributed computing with local connectivity. We show the gain of the so-called hardware plasticity induced by the ReSOM, where the system’s topology is not fixed by the user but learned along the system’s experience through self-organization.https://www.mdpi.com/2079-9292/9/10/1605brain-inspired computingreentryconvergence divergence zoneself-organizing mapshebbian learningmultimodal classification |
spellingShingle | Lyes Khacef Laurent Rodriguez Benoît Miramond Brain-Inspired Self-Organization with Cellular Neuromorphic Computing for Multimodal Unsupervised Learning Electronics brain-inspired computing reentry convergence divergence zone self-organizing maps hebbian learning multimodal classification |
title | Brain-Inspired Self-Organization with Cellular Neuromorphic Computing for Multimodal Unsupervised Learning |
title_full | Brain-Inspired Self-Organization with Cellular Neuromorphic Computing for Multimodal Unsupervised Learning |
title_fullStr | Brain-Inspired Self-Organization with Cellular Neuromorphic Computing for Multimodal Unsupervised Learning |
title_full_unstemmed | Brain-Inspired Self-Organization with Cellular Neuromorphic Computing for Multimodal Unsupervised Learning |
title_short | Brain-Inspired Self-Organization with Cellular Neuromorphic Computing for Multimodal Unsupervised Learning |
title_sort | brain inspired self organization with cellular neuromorphic computing for multimodal unsupervised learning |
topic | brain-inspired computing reentry convergence divergence zone self-organizing maps hebbian learning multimodal classification |
url | https://www.mdpi.com/2079-9292/9/10/1605 |
work_keys_str_mv | AT lyeskhacef braininspiredselforganizationwithcellularneuromorphiccomputingformultimodalunsupervisedlearning AT laurentrodriguez braininspiredselforganizationwithcellularneuromorphiccomputingformultimodalunsupervisedlearning AT benoitmiramond braininspiredselforganizationwithcellularneuromorphiccomputingformultimodalunsupervisedlearning |