Emulating Brain-like Rapid Learning in Neuromorphic Edge Computing

Achieving personalized intelligence at the edge with real-time learning capabilities holds enormous promise in enhancing our daily experiences and helping decision making, planning, and sensing. However, efficient and reliable edge learning remains difficult with current technology due to the lack o...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:arXiv.org 2024-08
Hauptverfasser: Stewart, Kenneth, Neumeier, Michael, Sumit Bam Shrestha, Orchard, Garrick, Neftci, Emre
Format: Artikel
Sprache:eng
Schlagworte:
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
container_end_page
container_issue
container_start_page
container_title arXiv.org
container_volume
creator Stewart, Kenneth
Neumeier, Michael
Sumit Bam Shrestha
Orchard, Garrick
Neftci, Emre
description Achieving personalized intelligence at the edge with real-time learning capabilities holds enormous promise in enhancing our daily experiences and helping decision making, planning, and sensing. However, efficient and reliable edge learning remains difficult with current technology due to the lack of personalized data, insufficient hardware capabilities, and inherent challenges posed by online learning. Over time and across multiple developmental stages, the brain has evolved to efficiently incorporate new knowledge by gradually building on previous knowledge. In this work, we emulate the multiple stages of learning with digital neuromorphic technology that simulates the neural and synaptic processes of the brain using two stages of learning. First, a meta-training stage trains the hyperparameters of synaptic plasticity for one-shot learning using a differentiable simulation of the neuromorphic hardware. This meta-training process refines a hardware local three-factor synaptic plasticity rule and its associated hyperparameters to align with the trained task domain. In a subsequent deployment stage, these optimized hyperparameters enable fast, data-efficient, and accurate learning of new classes. We demonstrate our approach using event-driven vision sensor data and the Intel Loihi neuromorphic processor with its plasticity dynamics, achieving real-time one-shot learning of new classes that is vastly improved over transfer learning. Our methodology can be deployed with arbitrary plasticity models and can be applied to situations demanding quick learning and adaptation at the edge, such as navigating unfamiliar environments or learning unexpected categories of data through user engagement.
format Article
fullrecord <record><control><sourceid>proquest</sourceid><recordid>TN_cdi_proquest_journals_3098382621</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>3098382621</sourcerecordid><originalsourceid>FETCH-proquest_journals_30983826213</originalsourceid><addsrcrecordid>eNqNi70KwjAYAIMgWLTvEHAupF9sjWtLxEEcxL0EG2tq_kya99eCD-B0w90tUAaUlgXbAaxQHuNICIF6D1VFM9Rwk7SYlB1wE4SyhVYvia_Cqx6fpQh2Nsrii0zBGRf8U90x7weJW2d8mscNWj6EjjL_cY22R35rT4UP7p1knLrRpWC_qqPkwCiDGkr6X_UBjPQ5fA</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>3098382621</pqid></control><display><type>article</type><title>Emulating Brain-like Rapid Learning in Neuromorphic Edge Computing</title><source>Free E- Journals</source><creator>Stewart, Kenneth ; Neumeier, Michael ; Sumit Bam Shrestha ; Orchard, Garrick ; Neftci, Emre</creator><creatorcontrib>Stewart, Kenneth ; Neumeier, Michael ; Sumit Bam Shrestha ; Orchard, Garrick ; Neftci, Emre</creatorcontrib><description>Achieving personalized intelligence at the edge with real-time learning capabilities holds enormous promise in enhancing our daily experiences and helping decision making, planning, and sensing. However, efficient and reliable edge learning remains difficult with current technology due to the lack of personalized data, insufficient hardware capabilities, and inherent challenges posed by online learning. Over time and across multiple developmental stages, the brain has evolved to efficiently incorporate new knowledge by gradually building on previous knowledge. In this work, we emulate the multiple stages of learning with digital neuromorphic technology that simulates the neural and synaptic processes of the brain using two stages of learning. First, a meta-training stage trains the hyperparameters of synaptic plasticity for one-shot learning using a differentiable simulation of the neuromorphic hardware. This meta-training process refines a hardware local three-factor synaptic plasticity rule and its associated hyperparameters to align with the trained task domain. In a subsequent deployment stage, these optimized hyperparameters enable fast, data-efficient, and accurate learning of new classes. We demonstrate our approach using event-driven vision sensor data and the Intel Loihi neuromorphic processor with its plasticity dynamics, achieving real-time one-shot learning of new classes that is vastly improved over transfer learning. Our methodology can be deployed with arbitrary plasticity models and can be applied to situations demanding quick learning and adaptation at the edge, such as navigating unfamiliar environments or learning unexpected categories of data through user engagement.</description><identifier>EISSN: 2331-8422</identifier><language>eng</language><publisher>Ithaca: Cornell University Library, arXiv.org</publisher><subject>Brain ; Customization ; Distance learning ; Edge computing ; Hardware ; Microprocessors ; Neuromorphic computing ; Real time</subject><ispartof>arXiv.org, 2024-08</ispartof><rights>2024. This work is published under http://creativecommons.org/licenses/by/4.0/ (the “License”). Notwithstanding the ProQuest Terms and Conditions, you may use this content in accordance with the terms of the License.</rights><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><link.rule.ids>776,780</link.rule.ids></links><search><creatorcontrib>Stewart, Kenneth</creatorcontrib><creatorcontrib>Neumeier, Michael</creatorcontrib><creatorcontrib>Sumit Bam Shrestha</creatorcontrib><creatorcontrib>Orchard, Garrick</creatorcontrib><creatorcontrib>Neftci, Emre</creatorcontrib><title>Emulating Brain-like Rapid Learning in Neuromorphic Edge Computing</title><title>arXiv.org</title><description>Achieving personalized intelligence at the edge with real-time learning capabilities holds enormous promise in enhancing our daily experiences and helping decision making, planning, and sensing. However, efficient and reliable edge learning remains difficult with current technology due to the lack of personalized data, insufficient hardware capabilities, and inherent challenges posed by online learning. Over time and across multiple developmental stages, the brain has evolved to efficiently incorporate new knowledge by gradually building on previous knowledge. In this work, we emulate the multiple stages of learning with digital neuromorphic technology that simulates the neural and synaptic processes of the brain using two stages of learning. First, a meta-training stage trains the hyperparameters of synaptic plasticity for one-shot learning using a differentiable simulation of the neuromorphic hardware. This meta-training process refines a hardware local three-factor synaptic plasticity rule and its associated hyperparameters to align with the trained task domain. In a subsequent deployment stage, these optimized hyperparameters enable fast, data-efficient, and accurate learning of new classes. We demonstrate our approach using event-driven vision sensor data and the Intel Loihi neuromorphic processor with its plasticity dynamics, achieving real-time one-shot learning of new classes that is vastly improved over transfer learning. Our methodology can be deployed with arbitrary plasticity models and can be applied to situations demanding quick learning and adaptation at the edge, such as navigating unfamiliar environments or learning unexpected categories of data through user engagement.</description><subject>Brain</subject><subject>Customization</subject><subject>Distance learning</subject><subject>Edge computing</subject><subject>Hardware</subject><subject>Microprocessors</subject><subject>Neuromorphic computing</subject><subject>Real time</subject><issn>2331-8422</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2024</creationdate><recordtype>article</recordtype><sourceid>ABUWG</sourceid><sourceid>AFKRA</sourceid><sourceid>AZQEC</sourceid><sourceid>BENPR</sourceid><sourceid>CCPQU</sourceid><sourceid>DWQXO</sourceid><recordid>eNqNi70KwjAYAIMgWLTvEHAupF9sjWtLxEEcxL0EG2tq_kya99eCD-B0w90tUAaUlgXbAaxQHuNICIF6D1VFM9Rwk7SYlB1wE4SyhVYvia_Cqx6fpQh2Nsrii0zBGRf8U90x7weJW2d8mscNWj6EjjL_cY22R35rT4UP7p1knLrRpWC_qqPkwCiDGkr6X_UBjPQ5fA</recordid><startdate>20240828</startdate><enddate>20240828</enddate><creator>Stewart, Kenneth</creator><creator>Neumeier, Michael</creator><creator>Sumit Bam Shrestha</creator><creator>Orchard, Garrick</creator><creator>Neftci, Emre</creator><general>Cornell University Library, arXiv.org</general><scope>8FE</scope><scope>8FG</scope><scope>ABJCF</scope><scope>ABUWG</scope><scope>AFKRA</scope><scope>AZQEC</scope><scope>BENPR</scope><scope>BGLVJ</scope><scope>CCPQU</scope><scope>DWQXO</scope><scope>HCIFZ</scope><scope>L6V</scope><scope>M7S</scope><scope>PIMPY</scope><scope>PQEST</scope><scope>PQQKQ</scope><scope>PQUKI</scope><scope>PRINS</scope><scope>PTHSS</scope></search><sort><creationdate>20240828</creationdate><title>Emulating Brain-like Rapid Learning in Neuromorphic Edge Computing</title><author>Stewart, Kenneth ; Neumeier, Michael ; Sumit Bam Shrestha ; Orchard, Garrick ; Neftci, Emre</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-proquest_journals_30983826213</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2024</creationdate><topic>Brain</topic><topic>Customization</topic><topic>Distance learning</topic><topic>Edge computing</topic><topic>Hardware</topic><topic>Microprocessors</topic><topic>Neuromorphic computing</topic><topic>Real time</topic><toplevel>online_resources</toplevel><creatorcontrib>Stewart, Kenneth</creatorcontrib><creatorcontrib>Neumeier, Michael</creatorcontrib><creatorcontrib>Sumit Bam Shrestha</creatorcontrib><creatorcontrib>Orchard, Garrick</creatorcontrib><creatorcontrib>Neftci, Emre</creatorcontrib><collection>ProQuest SciTech Collection</collection><collection>ProQuest Technology Collection</collection><collection>Materials Science &amp; Engineering Collection</collection><collection>ProQuest Central (Alumni Edition)</collection><collection>ProQuest Central UK/Ireland</collection><collection>ProQuest Central Essentials</collection><collection>ProQuest Central</collection><collection>Technology Collection</collection><collection>ProQuest One Community College</collection><collection>ProQuest Central Korea</collection><collection>SciTech Premium Collection</collection><collection>ProQuest Engineering Collection</collection><collection>Engineering Database</collection><collection>Publicly Available Content Database</collection><collection>ProQuest One Academic Eastern Edition (DO NOT USE)</collection><collection>ProQuest One Academic</collection><collection>ProQuest One Academic UKI Edition</collection><collection>ProQuest Central China</collection><collection>Engineering Collection</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Stewart, Kenneth</au><au>Neumeier, Michael</au><au>Sumit Bam Shrestha</au><au>Orchard, Garrick</au><au>Neftci, Emre</au><format>book</format><genre>document</genre><ristype>GEN</ristype><atitle>Emulating Brain-like Rapid Learning in Neuromorphic Edge Computing</atitle><jtitle>arXiv.org</jtitle><date>2024-08-28</date><risdate>2024</risdate><eissn>2331-8422</eissn><abstract>Achieving personalized intelligence at the edge with real-time learning capabilities holds enormous promise in enhancing our daily experiences and helping decision making, planning, and sensing. However, efficient and reliable edge learning remains difficult with current technology due to the lack of personalized data, insufficient hardware capabilities, and inherent challenges posed by online learning. Over time and across multiple developmental stages, the brain has evolved to efficiently incorporate new knowledge by gradually building on previous knowledge. In this work, we emulate the multiple stages of learning with digital neuromorphic technology that simulates the neural and synaptic processes of the brain using two stages of learning. First, a meta-training stage trains the hyperparameters of synaptic plasticity for one-shot learning using a differentiable simulation of the neuromorphic hardware. This meta-training process refines a hardware local three-factor synaptic plasticity rule and its associated hyperparameters to align with the trained task domain. In a subsequent deployment stage, these optimized hyperparameters enable fast, data-efficient, and accurate learning of new classes. We demonstrate our approach using event-driven vision sensor data and the Intel Loihi neuromorphic processor with its plasticity dynamics, achieving real-time one-shot learning of new classes that is vastly improved over transfer learning. Our methodology can be deployed with arbitrary plasticity models and can be applied to situations demanding quick learning and adaptation at the edge, such as navigating unfamiliar environments or learning unexpected categories of data through user engagement.</abstract><cop>Ithaca</cop><pub>Cornell University Library, arXiv.org</pub><oa>free_for_read</oa></addata></record>
fulltext fulltext
identifier EISSN: 2331-8422
ispartof arXiv.org, 2024-08
issn 2331-8422
language eng
recordid cdi_proquest_journals_3098382621
source Free E- Journals
subjects Brain
Customization
Distance learning
Edge computing
Hardware
Microprocessors
Neuromorphic computing
Real time
title Emulating Brain-like Rapid Learning in Neuromorphic Edge Computing
url https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-21T14%3A40%3A47IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-proquest&rft_val_fmt=info:ofi/fmt:kev:mtx:book&rft.genre=document&rft.atitle=Emulating%20Brain-like%20Rapid%20Learning%20in%20Neuromorphic%20Edge%20Computing&rft.jtitle=arXiv.org&rft.au=Stewart,%20Kenneth&rft.date=2024-08-28&rft.eissn=2331-8422&rft_id=info:doi/&rft_dat=%3Cproquest%3E3098382621%3C/proquest%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_pqid=3098382621&rft_id=info:pmid/&rfr_iscdi=true