A New Benchmark and Progress Toward Improved Weakly Supervised Learning

Knowledge Matters: Importance of Prior Information for Optimization [7], by Gulcehre et. al., sought to establish the limits of current black-box, deep learning techniques by posing problems which are difficult to learn without engineering knowledge into the model or training procedure. In our work,...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Ramapuram, Jason, Webb, Russ
Format: Artikel
Sprache:eng
Schlagworte:
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 Ramapuram, Jason
Webb, Russ
description Knowledge Matters: Importance of Prior Information for Optimization [7], by Gulcehre et. al., sought to establish the limits of current black-box, deep learning techniques by posing problems which are difficult to learn without engineering knowledge into the model or training procedure. In our work, we completely solve the previous Knowledge Matters problem using a generic model, pose a more difficult and scalable problem, All-Pairs, and advance this new problem by introducing a new learned, spatially-varying histogram model called TypeNet which outperforms conventional models on the problem. We present results on All-Pairs where our model achieves 100% test accuracy while the best ResNet models achieve 79% accuracy. In addition, our model is more than an order of magnitude smaller than Resnet-34. The challenge of solving larger-scale All-Pairs problems with high accuracy is presented to the community for investigation.
doi_str_mv 10.48550/arxiv.1807.00126
format Article
fullrecord <record><control><sourceid>arxiv_GOX</sourceid><recordid>TN_cdi_arxiv_primary_1807_00126</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>1807_00126</sourcerecordid><originalsourceid>FETCH-LOGICAL-a676-28aef7716d806b29bb93d430bd52a249c7a6f61f8c2776dbacd07a6d2865b5943</originalsourceid><addsrcrecordid>eNotj81Og0AURmfThak-gCvnBcCZgflh2TZam5BqIolLcoc7VNIWyCVS-_bS1tWXnMWXcxh7lCJOndbiGei3GWPphI2FkMrcsfWCb8OJL0NbfR-B9hxa5B_U7SgMAy-6ExDyzbGnbgzIvwLsD2f--dMHGpthInkAapt2d89mNRyG8PC_c1a8vhSrtyh_X29WizwCY02kHITaWmnQCeNV5n2WYJoIj1qBSrPKgqmNrF2lrDXooUIxIVTOaK-zNJmzp9vttaTsqZmkz-WlqLwWJX_zmkXs</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype></control><display><type>article</type><title>A New Benchmark and Progress Toward Improved Weakly Supervised Learning</title><source>arXiv.org</source><creator>Ramapuram, Jason ; Webb, Russ</creator><creatorcontrib>Ramapuram, Jason ; Webb, Russ</creatorcontrib><description>Knowledge Matters: Importance of Prior Information for Optimization [7], by Gulcehre et. al., sought to establish the limits of current black-box, deep learning techniques by posing problems which are difficult to learn without engineering knowledge into the model or training procedure. In our work, we completely solve the previous Knowledge Matters problem using a generic model, pose a more difficult and scalable problem, All-Pairs, and advance this new problem by introducing a new learned, spatially-varying histogram model called TypeNet which outperforms conventional models on the problem. We present results on All-Pairs where our model achieves 100% test accuracy while the best ResNet models achieve 79% accuracy. In addition, our model is more than an order of magnitude smaller than Resnet-34. The challenge of solving larger-scale All-Pairs problems with high accuracy is presented to the community for investigation.</description><identifier>DOI: 10.48550/arxiv.1807.00126</identifier><language>eng</language><subject>Computer Science - Learning ; Statistics - Machine Learning</subject><creationdate>2018-06</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>$$Tsyndetics_thumb_exl</thumbnail><link.rule.ids>228,230,776,881</link.rule.ids><linktorsrc>$$Uhttps://arxiv.org/abs/1807.00126$$EView_record_in_Cornell_University$$FView_record_in_$$GCornell_University$$Hfree_for_read</linktorsrc><backlink>$$Uhttps://doi.org/10.48550/arXiv.1807.00126$$DView paper in arXiv$$Hfree_for_read</backlink></links><search><creatorcontrib>Ramapuram, Jason</creatorcontrib><creatorcontrib>Webb, Russ</creatorcontrib><title>A New Benchmark and Progress Toward Improved Weakly Supervised Learning</title><description>Knowledge Matters: Importance of Prior Information for Optimization [7], by Gulcehre et. al., sought to establish the limits of current black-box, deep learning techniques by posing problems which are difficult to learn without engineering knowledge into the model or training procedure. In our work, we completely solve the previous Knowledge Matters problem using a generic model, pose a more difficult and scalable problem, All-Pairs, and advance this new problem by introducing a new learned, spatially-varying histogram model called TypeNet which outperforms conventional models on the problem. We present results on All-Pairs where our model achieves 100% test accuracy while the best ResNet models achieve 79% accuracy. In addition, our model is more than an order of magnitude smaller than Resnet-34. The challenge of solving larger-scale All-Pairs problems with high accuracy is presented to the community for investigation.</description><subject>Computer Science - Learning</subject><subject>Statistics - Machine Learning</subject><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2018</creationdate><recordtype>article</recordtype><sourceid>GOX</sourceid><recordid>eNotj81Og0AURmfThak-gCvnBcCZgflh2TZam5BqIolLcoc7VNIWyCVS-_bS1tWXnMWXcxh7lCJOndbiGei3GWPphI2FkMrcsfWCb8OJL0NbfR-B9hxa5B_U7SgMAy-6ExDyzbGnbgzIvwLsD2f--dMHGpthInkAapt2d89mNRyG8PC_c1a8vhSrtyh_X29WizwCY02kHITaWmnQCeNV5n2WYJoIj1qBSrPKgqmNrF2lrDXooUIxIVTOaK-zNJmzp9vttaTsqZmkz-WlqLwWJX_zmkXs</recordid><startdate>20180630</startdate><enddate>20180630</enddate><creator>Ramapuram, Jason</creator><creator>Webb, Russ</creator><scope>AKY</scope><scope>EPD</scope><scope>GOX</scope></search><sort><creationdate>20180630</creationdate><title>A New Benchmark and Progress Toward Improved Weakly Supervised Learning</title><author>Ramapuram, Jason ; Webb, Russ</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-a676-28aef7716d806b29bb93d430bd52a249c7a6f61f8c2776dbacd07a6d2865b5943</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2018</creationdate><topic>Computer Science - Learning</topic><topic>Statistics - Machine Learning</topic><toplevel>online_resources</toplevel><creatorcontrib>Ramapuram, Jason</creatorcontrib><creatorcontrib>Webb, Russ</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>Ramapuram, Jason</au><au>Webb, Russ</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>A New Benchmark and Progress Toward Improved Weakly Supervised Learning</atitle><date>2018-06-30</date><risdate>2018</risdate><abstract>Knowledge Matters: Importance of Prior Information for Optimization [7], by Gulcehre et. al., sought to establish the limits of current black-box, deep learning techniques by posing problems which are difficult to learn without engineering knowledge into the model or training procedure. In our work, we completely solve the previous Knowledge Matters problem using a generic model, pose a more difficult and scalable problem, All-Pairs, and advance this new problem by introducing a new learned, spatially-varying histogram model called TypeNet which outperforms conventional models on the problem. We present results on All-Pairs where our model achieves 100% test accuracy while the best ResNet models achieve 79% accuracy. In addition, our model is more than an order of magnitude smaller than Resnet-34. The challenge of solving larger-scale All-Pairs problems with high accuracy is presented to the community for investigation.</abstract><doi>10.48550/arxiv.1807.00126</doi><oa>free_for_read</oa></addata></record>
fulltext fulltext_linktorsrc
identifier DOI: 10.48550/arxiv.1807.00126
ispartof
issn
language eng
recordid cdi_arxiv_primary_1807_00126
source arXiv.org
subjects Computer Science - Learning
Statistics - Machine Learning
title A New Benchmark and Progress Toward Improved Weakly Supervised Learning
url https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-31T13%3A12%3A04IST&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=A%20New%20Benchmark%20and%20Progress%20Toward%20Improved%20Weakly%20Supervised%20Learning&rft.au=Ramapuram,%20Jason&rft.date=2018-06-30&rft_id=info:doi/10.48550/arxiv.1807.00126&rft_dat=%3Carxiv_GOX%3E1807_00126%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