Artificial Neural Networks for Neuroscientists: A Primer
Artificial neural networks (ANNs) are essential tools in machine learning that have drawn increasing attention in neuroscience. Besides offering powerful techniques for data analysis, ANNs provide a new approach for neuroscientists to build models for complex behaviors, heterogeneous neural activity...
Gespeichert in:
| Veröffentlicht in: | Neuron (Cambridge, Mass.) Mass.), 2020-09, Vol.107 (6), p.1048-1070 |
|---|---|
| Hauptverfasser: | , |
| Format: | Artikel |
| Sprache: | eng |
| Schlagworte: | |
| Online-Zugang: | Volltext |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| container_end_page | 1070 |
|---|---|
| container_issue | 6 |
| container_start_page | 1048 |
| container_title | Neuron (Cambridge, Mass.) |
| container_volume | 107 |
| creator | Yang, Guangyu Robert Wang, Xiao-Jing |
| description | Artificial neural networks (ANNs) are essential tools in machine learning that have drawn increasing attention in neuroscience. Besides offering powerful techniques for data analysis, ANNs provide a new approach for neuroscientists to build models for complex behaviors, heterogeneous neural activity, and circuit connectivity, as well as to explore optimization in neural systems, in ways that traditional models are not designed for. In this pedagogical Primer, we introduce ANNs and demonstrate how they have been fruitfully deployed to study neuroscientific questions. We first discuss basic concepts and methods of ANNs. Then, with a focus on bringing this mathematical framework closer to neurobiology, we detail how to customize the analysis, structure, and learning of ANNs to better address a wide range of challenges in brain research. To help readers garner hands-on experience, this Primer is accompanied with tutorial-style code in PyTorch and Jupyter Notebook, covering major topics.
Artificial neural networks (ANNs) are essential tools in modern machine learning. In this Primer, Yang and Wang introduce how new computational models based on ANNs can be built, analyzed, and customized to study a wide range of neuroscientific questions. |
| doi_str_mv | 10.1016/j.neuron.2020.09.005 |
| format | Article |
| fullrecord | <record><control><sourceid>proquest_pubme</sourceid><recordid>TN_cdi_pubmedcentral_primary_oai_pubmedcentral_nih_gov_11576090</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><els_id>S0896627320307054</els_id><sourcerecordid>2446662903</sourcerecordid><originalsourceid>FETCH-LOGICAL-c492t-85a7d78edf44695727e5eacf2cada36cf7fa29525dba02192f9f9ee1a9708ba03</originalsourceid><addsrcrecordid>eNp9kU9PGzEQxa2qVRPSfoMKReqFyy62117vcCiKIv5JiPbQni3jHYNDsqb2bhDfHiehCHrgNNL4N89v5hHyjdGSUVYfLsoOhxi6klNOSwolpfIDGTMKqhAM4CMZ0wbqouaqGpG9lBaUMiGBfSajioOiAGpMmlnsvfPWm-X0KuttS_8Q4l2auhC3vZCsx673qU9H09n0V_QrjF_IJ2eWCb8-1wn5c3rye35eXP48u5jPLgsrgPdFI41qVYOtE6IGqbhCicY6bk1rqto65QwHyWV7bShnwB04QGQmG2xyq5qQ453u_XC9wtZmI9mkvs8mTHzUwXj99qXzt_omrDVjUtUUNgoHzwox_B0w9Xrlk8Xl0nQYhqR5dlbXPJMZ_f4fughD7PJ-G0pWshJCZErsKJtPkyK6FzeM6k02eqF32ehNNpqCztnksf3Xm7wM_QsjAz92AOZ7rj1GvT28xdZHtL1ug3__hyfUW6KQ</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>2445353444</pqid></control><display><type>article</type><title>Artificial Neural Networks for Neuroscientists: A Primer</title><source>MEDLINE</source><source>Elsevier ScienceDirect Journals Complete</source><source>Open Access: Cell Press Free Archives</source><source>EZB Electronic Journals Library</source><creator>Yang, Guangyu Robert ; Wang, Xiao-Jing</creator><creatorcontrib>Yang, Guangyu Robert ; Wang, Xiao-Jing</creatorcontrib><description>Artificial neural networks (ANNs) are essential tools in machine learning that have drawn increasing attention in neuroscience. Besides offering powerful techniques for data analysis, ANNs provide a new approach for neuroscientists to build models for complex behaviors, heterogeneous neural activity, and circuit connectivity, as well as to explore optimization in neural systems, in ways that traditional models are not designed for. In this pedagogical Primer, we introduce ANNs and demonstrate how they have been fruitfully deployed to study neuroscientific questions. We first discuss basic concepts and methods of ANNs. Then, with a focus on bringing this mathematical framework closer to neurobiology, we detail how to customize the analysis, structure, and learning of ANNs to better address a wide range of challenges in brain research. To help readers garner hands-on experience, this Primer is accompanied with tutorial-style code in PyTorch and Jupyter Notebook, covering major topics.
Artificial neural networks (ANNs) are essential tools in modern machine learning. In this Primer, Yang and Wang introduce how new computational models based on ANNs can be built, analyzed, and customized to study a wide range of neuroscientific questions.</description><identifier>ISSN: 0896-6273</identifier><identifier>ISSN: 1097-4199</identifier><identifier>EISSN: 1097-4199</identifier><identifier>DOI: 10.1016/j.neuron.2020.09.005</identifier><identifier>PMID: 32970997</identifier><language>eng</language><publisher>United States: Elsevier Inc</publisher><subject>Algorithms ; Animal cognition ; Animals ; Architecture ; Artificial intelligence ; Attention ; Brain - physiology ; Brain research ; Deep learning ; Humans ; Ingredients ; Learning algorithms ; Machine learning ; Mathematical models ; Models, Neurological ; Nervous system ; Neural networks ; Neural Networks, Computer ; Neurophysiology ; Neurosciences</subject><ispartof>Neuron (Cambridge, Mass.), 2020-09, Vol.107 (6), p.1048-1070</ispartof><rights>2020 Elsevier Inc.</rights><rights>Copyright © 2020 Elsevier Inc. All rights reserved.</rights><rights>2020. Elsevier Inc.</rights><lds50>peer_reviewed</lds50><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed><citedby>FETCH-LOGICAL-c492t-85a7d78edf44695727e5eacf2cada36cf7fa29525dba02192f9f9ee1a9708ba03</citedby><cites>FETCH-LOGICAL-c492t-85a7d78edf44695727e5eacf2cada36cf7fa29525dba02192f9f9ee1a9708ba03</cites><orcidid>0000-0003-3124-8474</orcidid></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktohtml>$$Uhttps://dx.doi.org/10.1016/j.neuron.2020.09.005$$EHTML$$P50$$Gelsevier$$H</linktohtml><link.rule.ids>230,314,780,784,885,3548,27922,27923,45993</link.rule.ids><backlink>$$Uhttps://www.ncbi.nlm.nih.gov/pubmed/32970997$$D View this record in MEDLINE/PubMed$$Hfree_for_read</backlink></links><search><creatorcontrib>Yang, Guangyu Robert</creatorcontrib><creatorcontrib>Wang, Xiao-Jing</creatorcontrib><title>Artificial Neural Networks for Neuroscientists: A Primer</title><title>Neuron (Cambridge, Mass.)</title><addtitle>Neuron</addtitle><description>Artificial neural networks (ANNs) are essential tools in machine learning that have drawn increasing attention in neuroscience. Besides offering powerful techniques for data analysis, ANNs provide a new approach for neuroscientists to build models for complex behaviors, heterogeneous neural activity, and circuit connectivity, as well as to explore optimization in neural systems, in ways that traditional models are not designed for. In this pedagogical Primer, we introduce ANNs and demonstrate how they have been fruitfully deployed to study neuroscientific questions. We first discuss basic concepts and methods of ANNs. Then, with a focus on bringing this mathematical framework closer to neurobiology, we detail how to customize the analysis, structure, and learning of ANNs to better address a wide range of challenges in brain research. To help readers garner hands-on experience, this Primer is accompanied with tutorial-style code in PyTorch and Jupyter Notebook, covering major topics.
Artificial neural networks (ANNs) are essential tools in modern machine learning. In this Primer, Yang and Wang introduce how new computational models based on ANNs can be built, analyzed, and customized to study a wide range of neuroscientific questions.</description><subject>Algorithms</subject><subject>Animal cognition</subject><subject>Animals</subject><subject>Architecture</subject><subject>Artificial intelligence</subject><subject>Attention</subject><subject>Brain - physiology</subject><subject>Brain research</subject><subject>Deep learning</subject><subject>Humans</subject><subject>Ingredients</subject><subject>Learning algorithms</subject><subject>Machine learning</subject><subject>Mathematical models</subject><subject>Models, Neurological</subject><subject>Nervous system</subject><subject>Neural networks</subject><subject>Neural Networks, Computer</subject><subject>Neurophysiology</subject><subject>Neurosciences</subject><issn>0896-6273</issn><issn>1097-4199</issn><issn>1097-4199</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2020</creationdate><recordtype>article</recordtype><sourceid>EIF</sourceid><recordid>eNp9kU9PGzEQxa2qVRPSfoMKReqFyy62117vcCiKIv5JiPbQni3jHYNDsqb2bhDfHiehCHrgNNL4N89v5hHyjdGSUVYfLsoOhxi6klNOSwolpfIDGTMKqhAM4CMZ0wbqouaqGpG9lBaUMiGBfSajioOiAGpMmlnsvfPWm-X0KuttS_8Q4l2auhC3vZCsx673qU9H09n0V_QrjF_IJ2eWCb8-1wn5c3rye35eXP48u5jPLgsrgPdFI41qVYOtE6IGqbhCicY6bk1rqto65QwHyWV7bShnwB04QGQmG2xyq5qQ453u_XC9wtZmI9mkvs8mTHzUwXj99qXzt_omrDVjUtUUNgoHzwox_B0w9Xrlk8Xl0nQYhqR5dlbXPJMZ_f4fughD7PJ-G0pWshJCZErsKJtPkyK6FzeM6k02eqF32ehNNpqCztnksf3Xm7wM_QsjAz92AOZ7rj1GvT28xdZHtL1ug3__hyfUW6KQ</recordid><startdate>20200923</startdate><enddate>20200923</enddate><creator>Yang, Guangyu Robert</creator><creator>Wang, Xiao-Jing</creator><general>Elsevier Inc</general><general>Elsevier Limited</general><scope>CGR</scope><scope>CUY</scope><scope>CVF</scope><scope>ECM</scope><scope>EIF</scope><scope>NPM</scope><scope>AAYXX</scope><scope>CITATION</scope><scope>7QP</scope><scope>7QR</scope><scope>7TK</scope><scope>8FD</scope><scope>FR3</scope><scope>K9.</scope><scope>NAPCQ</scope><scope>P64</scope><scope>RC3</scope><scope>7X8</scope><scope>5PM</scope><orcidid>https://orcid.org/0000-0003-3124-8474</orcidid></search><sort><creationdate>20200923</creationdate><title>Artificial Neural Networks for Neuroscientists: A Primer</title><author>Yang, Guangyu Robert ; Wang, Xiao-Jing</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-c492t-85a7d78edf44695727e5eacf2cada36cf7fa29525dba02192f9f9ee1a9708ba03</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2020</creationdate><topic>Algorithms</topic><topic>Animal cognition</topic><topic>Animals</topic><topic>Architecture</topic><topic>Artificial intelligence</topic><topic>Attention</topic><topic>Brain - physiology</topic><topic>Brain research</topic><topic>Deep learning</topic><topic>Humans</topic><topic>Ingredients</topic><topic>Learning algorithms</topic><topic>Machine learning</topic><topic>Mathematical models</topic><topic>Models, Neurological</topic><topic>Nervous system</topic><topic>Neural networks</topic><topic>Neural Networks, Computer</topic><topic>Neurophysiology</topic><topic>Neurosciences</topic><toplevel>peer_reviewed</toplevel><toplevel>online_resources</toplevel><creatorcontrib>Yang, Guangyu Robert</creatorcontrib><creatorcontrib>Wang, Xiao-Jing</creatorcontrib><collection>Medline</collection><collection>MEDLINE</collection><collection>MEDLINE (Ovid)</collection><collection>MEDLINE</collection><collection>MEDLINE</collection><collection>PubMed</collection><collection>CrossRef</collection><collection>Calcium & Calcified Tissue Abstracts</collection><collection>Chemoreception Abstracts</collection><collection>Neurosciences Abstracts</collection><collection>Technology Research Database</collection><collection>Engineering Research Database</collection><collection>ProQuest Health & Medical Complete (Alumni)</collection><collection>Nursing & Allied Health Premium</collection><collection>Biotechnology and BioEngineering Abstracts</collection><collection>Genetics Abstracts</collection><collection>MEDLINE - Academic</collection><collection>PubMed Central (Full Participant titles)</collection><jtitle>Neuron (Cambridge, Mass.)</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Yang, Guangyu Robert</au><au>Wang, Xiao-Jing</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Artificial Neural Networks for Neuroscientists: A Primer</atitle><jtitle>Neuron (Cambridge, Mass.)</jtitle><addtitle>Neuron</addtitle><date>2020-09-23</date><risdate>2020</risdate><volume>107</volume><issue>6</issue><spage>1048</spage><epage>1070</epage><pages>1048-1070</pages><issn>0896-6273</issn><issn>1097-4199</issn><eissn>1097-4199</eissn><abstract>Artificial neural networks (ANNs) are essential tools in machine learning that have drawn increasing attention in neuroscience. Besides offering powerful techniques for data analysis, ANNs provide a new approach for neuroscientists to build models for complex behaviors, heterogeneous neural activity, and circuit connectivity, as well as to explore optimization in neural systems, in ways that traditional models are not designed for. In this pedagogical Primer, we introduce ANNs and demonstrate how they have been fruitfully deployed to study neuroscientific questions. We first discuss basic concepts and methods of ANNs. Then, with a focus on bringing this mathematical framework closer to neurobiology, we detail how to customize the analysis, structure, and learning of ANNs to better address a wide range of challenges in brain research. To help readers garner hands-on experience, this Primer is accompanied with tutorial-style code in PyTorch and Jupyter Notebook, covering major topics.
Artificial neural networks (ANNs) are essential tools in modern machine learning. In this Primer, Yang and Wang introduce how new computational models based on ANNs can be built, analyzed, and customized to study a wide range of neuroscientific questions.</abstract><cop>United States</cop><pub>Elsevier Inc</pub><pmid>32970997</pmid><doi>10.1016/j.neuron.2020.09.005</doi><tpages>23</tpages><orcidid>https://orcid.org/0000-0003-3124-8474</orcidid><oa>free_for_read</oa></addata></record> |
| fulltext | fulltext |
| identifier | ISSN: 0896-6273 |
| ispartof | Neuron (Cambridge, Mass.), 2020-09, Vol.107 (6), p.1048-1070 |
| issn | 0896-6273 1097-4199 1097-4199 |
| language | eng |
| recordid | cdi_pubmedcentral_primary_oai_pubmedcentral_nih_gov_11576090 |
| source | MEDLINE; Elsevier ScienceDirect Journals Complete; Open Access: Cell Press Free Archives; EZB Electronic Journals Library |
| subjects | Algorithms Animal cognition Animals Architecture Artificial intelligence Attention Brain - physiology Brain research Deep learning Humans Ingredients Learning algorithms Machine learning Mathematical models Models, Neurological Nervous system Neural networks Neural Networks, Computer Neurophysiology Neurosciences |
| title | Artificial Neural Networks for Neuroscientists: A Primer |
| url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-14T15%3A45%3A24IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-proquest_pubme&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=Artificial%20Neural%20Networks%20for%20Neuroscientists:%20A%20Primer&rft.jtitle=Neuron%20(Cambridge,%20Mass.)&rft.au=Yang,%20Guangyu%20Robert&rft.date=2020-09-23&rft.volume=107&rft.issue=6&rft.spage=1048&rft.epage=1070&rft.pages=1048-1070&rft.issn=0896-6273&rft.eissn=1097-4199&rft_id=info:doi/10.1016/j.neuron.2020.09.005&rft_dat=%3Cproquest_pubme%3E2446662903%3C/proquest_pubme%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_pqid=2445353444&rft_id=info:pmid/32970997&rft_els_id=S0896627320307054&rfr_iscdi=true |