Loading…
Explaining neural network predictions of material strength
We recently developed a deep learning method that can determine the critical peak stress of a material by looking at scanning electron microscope (SEM) images of the material's crystals. However, it has been somewhat unclear what kind of image features the network is keying off of when it makes...
Saved in:
Published in: | arXiv.org 2021-11 |
---|---|
Main Authors: | , , , |
Format: | Article |
Language: | English |
Subjects: | |
Online Access: | Get full text |
Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
cited_by | |
---|---|
cites | |
container_end_page | |
container_issue | |
container_start_page | |
container_title | arXiv.org |
container_volume | |
creator | Palmer, Ian A Mundhenk, T Nathan Gallagher, Brian Han, Yong |
description | We recently developed a deep learning method that can determine the critical peak stress of a material by looking at scanning electron microscope (SEM) images of the material's crystals. However, it has been somewhat unclear what kind of image features the network is keying off of when it makes its prediction. It is common in computer vision to employ an explainable AI saliency map to tell one what parts of an image are important to the network's decision. One can usually deduce the important features by looking at these salient locations. However, SEM images of crystals are more abstract to the human observer than natural image photographs. As a result, it is not easy to tell what features are important at the locations which are most salient. To solve this, we developed a method that helps us map features from important locations in SEM images to non-abstract textures that are easier to interpret. |
format | article |
fullrecord | <record><control><sourceid>proquest</sourceid><recordid>TN_cdi_proquest_journals_2595324714</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>2595324714</sourcerecordid><originalsourceid>FETCH-proquest_journals_25953247143</originalsourceid><addsrcrecordid>eNqNyjEOwiAUgGFiYmKjvQOJcxP6AKuupsYDuDdEaUtFwAdEj28HD-D0D9-_IAVwXld7AbAiZYwTYwx2DUjJC3JsP8Eq44wbqNMZlZ2T3h4fNKC-m1sy3kXqe_pUSaOZPSbUbkjjhix7ZaMuf12T7bm9ni5VQP_KOqZu8hndTB3Ig-Qgmlrw_64vJng3qg</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>2595324714</pqid></control><display><type>article</type><title>Explaining neural network predictions of material strength</title><source>Publicly Available Content (ProQuest)</source><creator>Palmer, Ian A ; Mundhenk, T Nathan ; Gallagher, Brian ; Han, Yong</creator><creatorcontrib>Palmer, Ian A ; Mundhenk, T Nathan ; Gallagher, Brian ; Han, Yong</creatorcontrib><description>We recently developed a deep learning method that can determine the critical peak stress of a material by looking at scanning electron microscope (SEM) images of the material's crystals. However, it has been somewhat unclear what kind of image features the network is keying off of when it makes its prediction. It is common in computer vision to employ an explainable AI saliency map to tell one what parts of an image are important to the network's decision. One can usually deduce the important features by looking at these salient locations. However, SEM images of crystals are more abstract to the human observer than natural image photographs. As a result, it is not easy to tell what features are important at the locations which are most salient. To solve this, we developed a method that helps us map features from important locations in SEM images to non-abstract textures that are easier to interpret.</description><identifier>EISSN: 2331-8422</identifier><language>eng</language><publisher>Ithaca: Cornell University Library, arXiv.org</publisher><subject>Computer vision ; Keying ; Neural networks ; Scanning electron microscopy</subject><ispartof>arXiv.org, 2021-11</ispartof><rights>2021. This work is published under http://arxiv.org/licenses/nonexclusive-distrib/1.0/ (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>$$Tsyndetics_thumb_exl</thumbnail><linktohtml>$$Uhttps://www.proquest.com/docview/2595324714?pq-origsite=primo$$EHTML$$P50$$Gproquest$$Hfree_for_read</linktohtml><link.rule.ids>780,784,25753,37012,44590</link.rule.ids></links><search><creatorcontrib>Palmer, Ian A</creatorcontrib><creatorcontrib>Mundhenk, T Nathan</creatorcontrib><creatorcontrib>Gallagher, Brian</creatorcontrib><creatorcontrib>Han, Yong</creatorcontrib><title>Explaining neural network predictions of material strength</title><title>arXiv.org</title><description>We recently developed a deep learning method that can determine the critical peak stress of a material by looking at scanning electron microscope (SEM) images of the material's crystals. However, it has been somewhat unclear what kind of image features the network is keying off of when it makes its prediction. It is common in computer vision to employ an explainable AI saliency map to tell one what parts of an image are important to the network's decision. One can usually deduce the important features by looking at these salient locations. However, SEM images of crystals are more abstract to the human observer than natural image photographs. As a result, it is not easy to tell what features are important at the locations which are most salient. To solve this, we developed a method that helps us map features from important locations in SEM images to non-abstract textures that are easier to interpret.</description><subject>Computer vision</subject><subject>Keying</subject><subject>Neural networks</subject><subject>Scanning electron microscopy</subject><issn>2331-8422</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2021</creationdate><recordtype>article</recordtype><sourceid>PIMPY</sourceid><recordid>eNqNyjEOwiAUgGFiYmKjvQOJcxP6AKuupsYDuDdEaUtFwAdEj28HD-D0D9-_IAVwXld7AbAiZYwTYwx2DUjJC3JsP8Eq44wbqNMZlZ2T3h4fNKC-m1sy3kXqe_pUSaOZPSbUbkjjhix7ZaMuf12T7bm9ni5VQP_KOqZu8hndTB3Ig-Qgmlrw_64vJng3qg</recordid><startdate>20211105</startdate><enddate>20211105</enddate><creator>Palmer, Ian A</creator><creator>Mundhenk, T Nathan</creator><creator>Gallagher, Brian</creator><creator>Han, Yong</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>20211105</creationdate><title>Explaining neural network predictions of material strength</title><author>Palmer, Ian A ; Mundhenk, T Nathan ; Gallagher, Brian ; Han, Yong</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-proquest_journals_25953247143</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2021</creationdate><topic>Computer vision</topic><topic>Keying</topic><topic>Neural networks</topic><topic>Scanning electron microscopy</topic><toplevel>online_resources</toplevel><creatorcontrib>Palmer, Ian A</creatorcontrib><creatorcontrib>Mundhenk, T Nathan</creatorcontrib><creatorcontrib>Gallagher, Brian</creatorcontrib><creatorcontrib>Han, Yong</creatorcontrib><collection>ProQuest SciTech Collection</collection><collection>ProQuest Technology Collection</collection><collection>Materials Science & Engineering Collection</collection><collection>ProQuest Central (Alumni)</collection><collection>ProQuest Central</collection><collection>ProQuest Central Essentials</collection><collection>ProQuest Central</collection><collection>Technology Collection</collection><collection>ProQuest One Community College</collection><collection>ProQuest Central</collection><collection>SciTech Premium Collection</collection><collection>ProQuest Engineering Collection</collection><collection>Engineering Database</collection><collection>Publicly Available Content (ProQuest)</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>Palmer, Ian A</au><au>Mundhenk, T Nathan</au><au>Gallagher, Brian</au><au>Han, Yong</au><format>book</format><genre>document</genre><ristype>GEN</ristype><atitle>Explaining neural network predictions of material strength</atitle><jtitle>arXiv.org</jtitle><date>2021-11-05</date><risdate>2021</risdate><eissn>2331-8422</eissn><abstract>We recently developed a deep learning method that can determine the critical peak stress of a material by looking at scanning electron microscope (SEM) images of the material's crystals. However, it has been somewhat unclear what kind of image features the network is keying off of when it makes its prediction. It is common in computer vision to employ an explainable AI saliency map to tell one what parts of an image are important to the network's decision. One can usually deduce the important features by looking at these salient locations. However, SEM images of crystals are more abstract to the human observer than natural image photographs. As a result, it is not easy to tell what features are important at the locations which are most salient. To solve this, we developed a method that helps us map features from important locations in SEM images to non-abstract textures that are easier to interpret.</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, 2021-11 |
issn | 2331-8422 |
language | eng |
recordid | cdi_proquest_journals_2595324714 |
source | Publicly Available Content (ProQuest) |
subjects | Computer vision Keying Neural networks Scanning electron microscopy |
title | Explaining neural network predictions of material strength |
url | http://sfxeu10.hosted.exlibrisgroup.com/loughborough?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2024-12-24T14%3A35%3A01IST&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=Explaining%20neural%20network%20predictions%20of%20material%20strength&rft.jtitle=arXiv.org&rft.au=Palmer,%20Ian%20A&rft.date=2021-11-05&rft.eissn=2331-8422&rft_id=info:doi/&rft_dat=%3Cproquest%3E2595324714%3C/proquest%3E%3Cgrp_id%3Ecdi_FETCH-proquest_journals_25953247143%3C/grp_id%3E%3Coa%3E%3C/oa%3E%3Curl%3E%3C/url%3E&rft_id=info:oai/&rft_pqid=2595324714&rft_id=info:pmid/&rfr_iscdi=true |