{"id":845017,"date":"2022-05-18T06:13:12","date_gmt":"2022-05-18T13:13:12","guid":{"rendered":"https:\/\/www.microsoft.com\/en-us\/research\/?post_type=msr-research-item&#038;p=845017"},"modified":"2023-02-21T02:54:10","modified_gmt":"2023-02-21T10:54:10","slug":"is-explainable-ai-a-race-against-model-complexity","status":"publish","type":"msr-research-item","link":"https:\/\/www.microsoft.com\/en-us\/research\/publication\/is-explainable-ai-a-race-against-model-complexity\/","title":{"rendered":"Is explainable AI a race against model complexity?"},"content":{"rendered":"<p><span dir=\"ltr\" role=\"presentation\">Explaining the behaviour of intelligent systems will get increasingly and perhaps intractably challenging as models grow in <\/span><span dir=\"ltr\" role=\"presentation\">size and complexity. We may not be able to expect an explanation for every prediction made by a brain-scale model, nor can <\/span><span dir=\"ltr\" role=\"presentation\">we expect explanations to remain objective or apolitical. Our functionalist understanding of these models is of less advantage <\/span><span dir=\"ltr\" role=\"presentation\">than we might assume. Models precede explanations, and can be useful even when both model and explanation are incorrect. <\/span><span dir=\"ltr\" role=\"presentation\">Explainability may never win the race against complexity, but this is less problematic than it seems.<\/span><\/p>\n","protected":false},"excerpt":{"rendered":"<p>Explaining the behaviour of intelligent systems will get increasingly and perhaps intractably challenging as models grow in size and complexity. We may not be able to expect an explanation for every prediction made by a brain-scale model, nor can we expect explanations to remain objective or apolitical. Our functionalist understanding of these models is of [&hellip;]<\/p>\n","protected":false},"featured_media":0,"template":"","meta":{"msr-url-field":"","msr-podcast-episode":"","msrModifiedDate":"","msrModifiedDateEnabled":false,"ep_exclude_from_search":false,"_classifai_error":"","footnotes":""},"msr-content-type":[3],"msr-research-highlight":[],"research-area":[13556,13554,13560],"msr-publication-type":[193716],"msr-product-type":[],"msr-focus-area":[],"msr-platform":[],"msr-download-source":[],"msr-locale":[268875],"msr-post-option":[],"msr-field-of-study":[246694,246658,248485,246685,251989],"msr-conference":[],"msr-journal":[],"msr-impact-theme":[],"msr-pillar":[],"class_list":["post-845017","msr-research-item","type-msr-research-item","status-publish","hentry","msr-research-area-artificial-intelligence","msr-research-area-human-computer-interaction","msr-research-area-programming-languages-software-engineering","msr-locale-en_us","msr-field-of-study-artificial-intelligence","msr-field-of-study-deep-learning","msr-field-of-study-human-computer-interaction","msr-field-of-study-machine-learning","msr-field-of-study-user-experience-design"],"msr_publishername":"CEUR Workshop Proceedings","msr_edition":"","msr_affiliation":"","msr_published_date":"2022-3-1","msr_host":"","msr_duration":"","msr_version":"","msr_speaker":"","msr_other_contributors":"","msr_booktitle":"","msr_pages_string":"","msr_chapter":"","msr_isbn":"","msr_journal":"","msr_volume":"","msr_number":"","msr_editors":"","msr_series":"","msr_issue":"","msr_organization":"","msr_how_published":"","msr_notes":"","msr_highlight_text":"","msr_release_tracker_id":"","msr_original_fields_of_study":"","msr_download_urls":"","msr_external_url":"","msr_secondary_video_url":"","msr_longbiography":"","msr_microsoftintellectualproperty":1,"msr_main_download":"","msr_publicationurl":"","msr_doi":"","msr_publication_uploader":[{"type":"file","viewUrl":"https:\/\/www.microsoft.com\/en-us\/research\/uploads\/prod\/2022\/05\/sarkar_2022_explainable.pdf","id":"845020","title":"sarkar_2022_explainable","label_id":"243132","label":0}],"msr_related_uploader":"","msr_attachments":[{"id":845020,"url":"https:\/\/www.microsoft.com\/en-us\/research\/uploads\/prod\/2022\/05\/sarkar_2022_explainable.pdf"}],"msr-author-ordering":[{"type":"user_nicename","value":"Advait Sarkar","user_id":37146,"rest_url":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/microsoft-research\/v1\/researchers?person=Advait Sarkar"}],"msr_impact_theme":[],"msr_research_lab":[199561],"msr_event":[],"msr_group":[913161],"msr_project":[511097],"publication":[],"video":[],"download":[],"msr_publication_type":"inproceedings","related_content":{"projects":[{"ID":511097,"post_title":"Calc Intelligence","post_name":"calc-intelligence","post_type":"msr-project","post_date":"2020-02-17 06:40:29","post_modified":"2023-11-27 06:33:39","post_status":"publish","permalink":"https:\/\/www.microsoft.com\/en-us\/research\/project\/calc-intelligence\/","post_excerpt":"By Calc Intelligence, we mean the research goal of bringing intelligence to end-user programming, and in particular to spreadsheets.","_links":{"self":[{"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-project\/511097"}]}}]},"_links":{"self":[{"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-research-item\/845017"}],"collection":[{"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-research-item"}],"about":[{"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/types\/msr-research-item"}],"version-history":[{"count":1,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-research-item\/845017\/revisions"}],"predecessor-version":[{"id":845023,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-research-item\/845017\/revisions\/845023"}],"wp:attachment":[{"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/media?parent=845017"}],"wp:term":[{"taxonomy":"msr-content-type","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-content-type?post=845017"},{"taxonomy":"msr-research-highlight","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-research-highlight?post=845017"},{"taxonomy":"msr-research-area","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/research-area?post=845017"},{"taxonomy":"msr-publication-type","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-publication-type?post=845017"},{"taxonomy":"msr-product-type","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-product-type?post=845017"},{"taxonomy":"msr-focus-area","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-focus-area?post=845017"},{"taxonomy":"msr-platform","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-platform?post=845017"},{"taxonomy":"msr-download-source","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-download-source?post=845017"},{"taxonomy":"msr-locale","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-locale?post=845017"},{"taxonomy":"msr-post-option","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-post-option?post=845017"},{"taxonomy":"msr-field-of-study","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-field-of-study?post=845017"},{"taxonomy":"msr-conference","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-conference?post=845017"},{"taxonomy":"msr-journal","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-journal?post=845017"},{"taxonomy":"msr-impact-theme","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-impact-theme?post=845017"},{"taxonomy":"msr-pillar","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-pillar?post=845017"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}