Learning Neural Activations

Learning Neural Activations

An artificial neuron is modelled as a weighted summation followed by an activation function which determines its output. A wide variety of activation functions such as rectified linear units (ReLU), leaky-ReLU, Swish, MISH, etc. have been explored in the literature. In this short paper, we explore w...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Minhas, Fayyaz ul Amir Afsar, Asif, Amina
Format: Artikel
Sprache:eng
Schlagworte:
Computer Science - Learning
Computer Science - Neural and Evolutionary Computing
Statistics - Machine Learning
Online-Zugang:Volltext bestellen
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
container_end_page
container_issue
container_start_page
container_title
container_volume
creator Minhas, Fayyaz ul Amir Afsar
Asif, Amina
description An artificial neuron is modelled as a weighted summation followed by an activation function which determines its output. A wide variety of activation functions such as rectified linear units (ReLU), leaky-ReLU, Swish, MISH, etc. have been explored in the literature. In this short paper, we explore what happens when the activation function of each neuron in an artificial neural network is learned natively from data alone. This is achieved by modelling the activation function of each neuron as a small neural network whose weights are shared by all neurons in the original network. We list our primary findings in the conclusions section. The code for our analysis is available at: https://github.com/amina01/Learning-Neural-Activations.
doi_str_mv 10.48550/arxiv.1912.12187
format Article
fullrecord <record><control><sourceid>arxiv_GOX</sourceid><recordid>TN_cdi_arxiv_primary_1912_12187</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>1912_12187</sourcerecordid><originalsourceid>FETCH-LOGICAL-a677-222604e13941ef80aa60ff89a9340260fc66874cbb230a0e33890d157c08c3eb3</originalsourceid><addsrcrecordid>eNotzrsKwjAYhuEsDqJegDjoDbT-OTSHUYonKLq4l78xkYBWibXo3avV6Rte-HgIGVNIhc4ymGN8hjalhrKUMqpVn0wKh7EO9Wm2c4-I59nCNqHFJlzr-5D0PJ7vbvTfATmslod8kxT79TZfFAlKpRLGmAThKDeCOq8BUYL32qDhAj7JWym1EraqGAcEx7k2cKSZsqAtdxUfkOnvttOVtxguGF_lV1l2Sv4GBQc1MQ</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype></control><display><type>article</type><title>Learning Neural Activations</title><source>arXiv.org</source><creator>Minhas, Fayyaz ul Amir Afsar ; Asif, Amina</creator><creatorcontrib>Minhas, Fayyaz ul Amir Afsar ; Asif, Amina</creatorcontrib><description>An artificial neuron is modelled as a weighted summation followed by an activation function which determines its output. A wide variety of activation functions such as rectified linear units (ReLU), leaky-ReLU, Swish, MISH, etc. have been explored in the literature. In this short paper, we explore what happens when the activation function of each neuron in an artificial neural network is learned natively from data alone. This is achieved by modelling the activation function of each neuron as a small neural network whose weights are shared by all neurons in the original network. We list our primary findings in the conclusions section. The code for our analysis is available at: https://github.com/amina01/Learning-Neural-Activations.</description><identifier>DOI: 10.48550/arxiv.1912.12187</identifier><language>eng</language><subject>Computer Science - Learning ; Computer Science - Neural and Evolutionary Computing ; Statistics - Machine Learning</subject><creationdate>2019-12</creationdate><rights>http://arxiv.org/licenses/nonexclusive-distrib/1.0</rights><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><link.rule.ids>228,230,780,885</link.rule.ids><linktorsrc>$$Uhttps://arxiv.org/abs/1912.12187$$EView_record_in_Cornell_University$$FView_record_in_$$GCornell_University$$Hfree_for_read</linktorsrc><backlink>$$Uhttps://doi.org/10.48550/arXiv.1912.12187$$DView paper in arXiv$$Hfree_for_read</backlink></links><search><creatorcontrib>Minhas, Fayyaz ul Amir Afsar</creatorcontrib><creatorcontrib>Asif, Amina</creatorcontrib><title>Learning Neural Activations</title><description>An artificial neuron is modelled as a weighted summation followed by an activation function which determines its output. A wide variety of activation functions such as rectified linear units (ReLU), leaky-ReLU, Swish, MISH, etc. have been explored in the literature. In this short paper, we explore what happens when the activation function of each neuron in an artificial neural network is learned natively from data alone. This is achieved by modelling the activation function of each neuron as a small neural network whose weights are shared by all neurons in the original network. We list our primary findings in the conclusions section. The code for our analysis is available at: https://github.com/amina01/Learning-Neural-Activations.</description><subject>Computer Science - Learning</subject><subject>Computer Science - Neural and Evolutionary Computing</subject><subject>Statistics - Machine Learning</subject><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2019</creationdate><recordtype>article</recordtype><sourceid>GOX</sourceid><recordid>eNotzrsKwjAYhuEsDqJegDjoDbT-OTSHUYonKLq4l78xkYBWibXo3avV6Rte-HgIGVNIhc4ymGN8hjalhrKUMqpVn0wKh7EO9Wm2c4-I59nCNqHFJlzr-5D0PJ7vbvTfATmslod8kxT79TZfFAlKpRLGmAThKDeCOq8BUYL32qDhAj7JWym1EraqGAcEx7k2cKSZsqAtdxUfkOnvttOVtxguGF_lV1l2Sv4GBQc1MQ</recordid><startdate>20191227</startdate><enddate>20191227</enddate><creator>Minhas, Fayyaz ul Amir Afsar</creator><creator>Asif, Amina</creator><scope>AKY</scope><scope>EPD</scope><scope>GOX</scope></search><sort><creationdate>20191227</creationdate><title>Learning Neural Activations</title><author>Minhas, Fayyaz ul Amir Afsar ; Asif, Amina</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-a677-222604e13941ef80aa60ff89a9340260fc66874cbb230a0e33890d157c08c3eb3</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2019</creationdate><topic>Computer Science - Learning</topic><topic>Computer Science - Neural and Evolutionary Computing</topic><topic>Statistics - Machine Learning</topic><toplevel>online_resources</toplevel><creatorcontrib>Minhas, Fayyaz ul Amir Afsar</creatorcontrib><creatorcontrib>Asif, Amina</creatorcontrib><collection>arXiv Computer Science</collection><collection>arXiv Statistics</collection><collection>arXiv.org</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>Minhas, Fayyaz ul Amir Afsar</au><au>Asif, Amina</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Learning Neural Activations</atitle><date>2019-12-27</date><risdate>2019</risdate><abstract>An artificial neuron is modelled as a weighted summation followed by an activation function which determines its output. A wide variety of activation functions such as rectified linear units (ReLU), leaky-ReLU, Swish, MISH, etc. have been explored in the literature. In this short paper, we explore what happens when the activation function of each neuron in an artificial neural network is learned natively from data alone. This is achieved by modelling the activation function of each neuron as a small neural network whose weights are shared by all neurons in the original network. We list our primary findings in the conclusions section. The code for our analysis is available at: https://github.com/amina01/Learning-Neural-Activations.</abstract><doi>10.48550/arxiv.1912.12187</doi><oa>free_for_read</oa></addata></record>
fulltext fulltext_linktorsrc
identifier DOI: 10.48550/arxiv.1912.12187
ispartof
issn
language eng
recordid cdi_arxiv_primary_1912_12187
source arXiv.org
subjects Computer Science - Learning
Computer Science - Neural and Evolutionary Computing
Statistics - Machine Learning
title Learning Neural Activations
url https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-12T15%3A12%3A24IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-arxiv_GOX&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=Learning%20Neural%20Activations&rft.au=Minhas,%20Fayyaz%20ul%20Amir%20Afsar&rft.date=2019-12-27&rft_id=info:doi/10.48550/arxiv.1912.12187&rft_dat=%3Carxiv_GOX%3E1912_12187%3C/arxiv_GOX%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_id=info:pmid/&rfr_iscdi=true