A copula-based visualization technique for a neural network
Interpretability of machine learning is defined as the extent to which humans can comprehend the reason of a decision. However, a neural network is not considered interpretable due to the ambiguity in its decision-making process. Therefore, in this study, we propose a new algorithm that reveals whic...
Gespeichert in:
Hauptverfasser: | , , , |
---|---|
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 | Kubo, Yusuke Komori, Yuto Okuyama, Toyonobu Tokieda, Hiroshi |
description | Interpretability of machine learning is defined as the extent to which humans
can comprehend the reason of a decision. However, a neural network is not
considered interpretable due to the ambiguity in its decision-making process.
Therefore, in this study, we propose a new algorithm that reveals which feature
values the trained neural network considers important and which paths are
mainly traced in the process of decision-making. In the proposed algorithm, the
score estimated by the correlation coefficients between the neural network
layers that can be calculated by applying the concept of a pair copula was
defined. We compared the estimated score with the feature importance values of
Random Forest, which is sometimes regarded as a highly interpretable algorithm,
in the experiment and confirmed that the results were consistent with each
other. This algorithm suggests an approach for compressing a neural network and
its parameter tuning because the algorithm identifies the paths that contribute
to the classification or prediction results. |
doi_str_mv | 10.48550/arxiv.2003.12317 |
format | Article |
fullrecord | <record><control><sourceid>arxiv_GOX</sourceid><recordid>TN_cdi_arxiv_primary_2003_12317</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>2003_12317</sourcerecordid><originalsourceid>FETCH-LOGICAL-a677-5468e36cd99de297903682479d91c6edd7c81229717992a1c7eb34c964f520a33</originalsourceid><addsrcrecordid>eNotj71uwjAURr10qKAP0Am_QFL_xc4VE0L9QULqwh5d7BthERLqJLTl6aHQ6Qyf9Okcxp6lyE1ZFOIF00885UoInUulpXtk8wX33XFsMNtiT4GfYj9iE884xK7lA_ldG79G4nWXOPKWxoTNFcN3l_ZT9lBj09PTPyds8_a6WX5k68_31XKxztA6lxXGlqStDwCBFDgQ2pbKOAggvaUQnC-lug7SASiU3tFWGw_W1IUSqPWEze63N_vqmOIB02_1V1HdKvQFWftBHA</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype></control><display><type>article</type><title>A copula-based visualization technique for a neural network</title><source>arXiv.org</source><creator>Kubo, Yusuke ; Komori, Yuto ; Okuyama, Toyonobu ; Tokieda, Hiroshi</creator><creatorcontrib>Kubo, Yusuke ; Komori, Yuto ; Okuyama, Toyonobu ; Tokieda, Hiroshi</creatorcontrib><description>Interpretability of machine learning is defined as the extent to which humans
can comprehend the reason of a decision. However, a neural network is not
considered interpretable due to the ambiguity in its decision-making process.
Therefore, in this study, we propose a new algorithm that reveals which feature
values the trained neural network considers important and which paths are
mainly traced in the process of decision-making. In the proposed algorithm, the
score estimated by the correlation coefficients between the neural network
layers that can be calculated by applying the concept of a pair copula was
defined. We compared the estimated score with the feature importance values of
Random Forest, which is sometimes regarded as a highly interpretable algorithm,
in the experiment and confirmed that the results were consistent with each
other. This algorithm suggests an approach for compressing a neural network and
its parameter tuning because the algorithm identifies the paths that contribute
to the classification or prediction results.</description><identifier>DOI: 10.48550/arxiv.2003.12317</identifier><language>eng</language><subject>Computer Science - Learning ; Statistics - Machine Learning</subject><creationdate>2020-03</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/2003.12317$$EView_record_in_Cornell_University$$FView_record_in_$$GCornell_University$$Hfree_for_read</linktorsrc><backlink>$$Uhttps://doi.org/10.48550/arXiv.2003.12317$$DView paper in arXiv$$Hfree_for_read</backlink></links><search><creatorcontrib>Kubo, Yusuke</creatorcontrib><creatorcontrib>Komori, Yuto</creatorcontrib><creatorcontrib>Okuyama, Toyonobu</creatorcontrib><creatorcontrib>Tokieda, Hiroshi</creatorcontrib><title>A copula-based visualization technique for a neural network</title><description>Interpretability of machine learning is defined as the extent to which humans
can comprehend the reason of a decision. However, a neural network is not
considered interpretable due to the ambiguity in its decision-making process.
Therefore, in this study, we propose a new algorithm that reveals which feature
values the trained neural network considers important and which paths are
mainly traced in the process of decision-making. In the proposed algorithm, the
score estimated by the correlation coefficients between the neural network
layers that can be calculated by applying the concept of a pair copula was
defined. We compared the estimated score with the feature importance values of
Random Forest, which is sometimes regarded as a highly interpretable algorithm,
in the experiment and confirmed that the results were consistent with each
other. This algorithm suggests an approach for compressing a neural network and
its parameter tuning because the algorithm identifies the paths that contribute
to the classification or prediction results.</description><subject>Computer Science - Learning</subject><subject>Statistics - Machine Learning</subject><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2020</creationdate><recordtype>article</recordtype><sourceid>GOX</sourceid><recordid>eNotj71uwjAURr10qKAP0Am_QFL_xc4VE0L9QULqwh5d7BthERLqJLTl6aHQ6Qyf9Okcxp6lyE1ZFOIF00885UoInUulpXtk8wX33XFsMNtiT4GfYj9iE884xK7lA_ldG79G4nWXOPKWxoTNFcN3l_ZT9lBj09PTPyds8_a6WX5k68_31XKxztA6lxXGlqStDwCBFDgQ2pbKOAggvaUQnC-lug7SASiU3tFWGw_W1IUSqPWEze63N_vqmOIB02_1V1HdKvQFWftBHA</recordid><startdate>20200327</startdate><enddate>20200327</enddate><creator>Kubo, Yusuke</creator><creator>Komori, Yuto</creator><creator>Okuyama, Toyonobu</creator><creator>Tokieda, Hiroshi</creator><scope>AKY</scope><scope>EPD</scope><scope>GOX</scope></search><sort><creationdate>20200327</creationdate><title>A copula-based visualization technique for a neural network</title><author>Kubo, Yusuke ; Komori, Yuto ; Okuyama, Toyonobu ; Tokieda, Hiroshi</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-a677-5468e36cd99de297903682479d91c6edd7c81229717992a1c7eb34c964f520a33</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2020</creationdate><topic>Computer Science - Learning</topic><topic>Statistics - Machine Learning</topic><toplevel>online_resources</toplevel><creatorcontrib>Kubo, Yusuke</creatorcontrib><creatorcontrib>Komori, Yuto</creatorcontrib><creatorcontrib>Okuyama, Toyonobu</creatorcontrib><creatorcontrib>Tokieda, Hiroshi</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>Kubo, Yusuke</au><au>Komori, Yuto</au><au>Okuyama, Toyonobu</au><au>Tokieda, Hiroshi</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>A copula-based visualization technique for a neural network</atitle><date>2020-03-27</date><risdate>2020</risdate><abstract>Interpretability of machine learning is defined as the extent to which humans
can comprehend the reason of a decision. However, a neural network is not
considered interpretable due to the ambiguity in its decision-making process.
Therefore, in this study, we propose a new algorithm that reveals which feature
values the trained neural network considers important and which paths are
mainly traced in the process of decision-making. In the proposed algorithm, the
score estimated by the correlation coefficients between the neural network
layers that can be calculated by applying the concept of a pair copula was
defined. We compared the estimated score with the feature importance values of
Random Forest, which is sometimes regarded as a highly interpretable algorithm,
in the experiment and confirmed that the results were consistent with each
other. This algorithm suggests an approach for compressing a neural network and
its parameter tuning because the algorithm identifies the paths that contribute
to the classification or prediction results.</abstract><doi>10.48550/arxiv.2003.12317</doi><oa>free_for_read</oa></addata></record> |
fulltext | fulltext_linktorsrc |
identifier | DOI: 10.48550/arxiv.2003.12317 |
ispartof | |
issn | |
language | eng |
recordid | cdi_arxiv_primary_2003_12317 |
source | arXiv.org |
subjects | Computer Science - Learning Statistics - Machine Learning |
title | A copula-based visualization technique for a neural network |
url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-02-01T06%3A07%3A22IST&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%20copula-based%20visualization%20technique%20for%20a%20neural%20network&rft.au=Kubo,%20Yusuke&rft.date=2020-03-27&rft_id=info:doi/10.48550/arxiv.2003.12317&rft_dat=%3Carxiv_GOX%3E2003_12317%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 |