{"id":1542,"date":"2021-05-27T09:44:53","date_gmt":"2021-05-27T16:44:53","guid":{"rendered":"https:\/\/www.microsoft.com\/en-us\/haxtoolkit\/?post_type=example&p=1542"},"modified":"2023-05-26T05:07:19","modified_gmt":"2023-05-26T12:07:19","slug":"neural-net-g11-f-example-based-explanations","status":"publish","type":"example","link":"https:\/\/www.microsoft.com\/en-us\/haxtoolkit\/example\/neural-net-g11-f-example-based-explanations\/","title":{"rendered":"Image recognition | 11F: Example-based explanations"},"content":{"rendered":"
\n\t\n\n

Image recognition | 11F: Example-based explanations<\/h2>\n\n\n\n
\"\"<\/figure>\n\n<\/div>\n\n\n\n\n\n
\"How
To make clear why the AI system behaved as it did (Guideline 11<\/a>), an example-based explanation (Pattern 11F<\/a>) was used to demonstrate how a neural net system recognizes an avocado from a drawing (Cai et al., 2019<\/a>). In this case, the explanation shows examples of drawings that taught the system what an avocado looks like. Image captured July 2020.<\/sub><\/sup><\/em><\/figcaption><\/figure>\n","protected":false},"featured_media":1359,"menu_order":0,"template":"","meta":{"toolkit_pattern_number":"11F","ep_exclude_from_search":false,"footnotes":""},"application-type":[60],"goal":[114,126,123],"guideline-term":[13],"product-category":[28],"class_list":["post-1542","example","type-example","status-publish","has-post-thumbnail","hentry","application-type-image-recognition","goal-appropriate-reliance","goal-reliability","goal-transparency","guideline-term-make-clear-why-the-system-did-what-it-did","product-category-productivity"],"yoast_head":"\nImage recognition | 11F: Example-based explanations - Microsoft HAX Toolkit<\/title>\n<meta name=\"robots\" content=\"index, follow, max-snippet:-1, max-image-preview:large, max-video-preview:-1\" \/>\n<link rel=\"canonical\" href=\"https:\/\/www.microsoft.com\/en-us\/haxtoolkit\/example\/neural-net-g11-f-example-based-explanations\/\" \/>\n<meta property=\"og:locale\" content=\"en_US\" \/>\n<meta property=\"og:type\" content=\"article\" \/>\n<meta property=\"og:title\" content=\"Image recognition | 11F: Example-based explanations - Microsoft HAX Toolkit\" \/>\n<meta property=\"og:url\" content=\"https:\/\/www.microsoft.com\/en-us\/haxtoolkit\/example\/neural-net-g11-f-example-based-explanations\/\" \/>\n<meta property=\"og:site_name\" content=\"Microsoft HAX Toolkit\" \/>\n<meta property=\"article:modified_time\" content=\"2023-05-26T12:07:19+00:00\" \/>\n<meta property=\"og:image\" content=\"https:\/\/www.microsoft.com\/en-us\/haxtoolkit\/uploads\/prod\/2021\/05\/G11-F_Example-Based-Explanations_Google-Draw-annotated.png\" \/>\n\t<meta property=\"og:image:width\" content=\"768\" \/>\n\t<meta property=\"og:image:height\" content=\"954\" \/>\n\t<meta property=\"og:image:type\" content=\"image\/png\" \/>\n<meta name=\"twitter:card\" content=\"summary_large_image\" \/>\n<meta name=\"twitter:label1\" content=\"Est. reading time\" \/>\n\t<meta name=\"twitter:data1\" content=\"1 minute\" \/>\n\t<meta name=\"twitter:label2\" content=\"Written by\" \/>\n\t<meta name=\"twitter:data2\" content=\"Shipi Dhanorkar\" \/>\n<script type=\"application\/ld+json\" class=\"yoast-schema-graph\">{\"@context\":\"https:\/\/schema.org\",\"@graph\":[{\"@type\":\"WebPage\",\"@id\":\"https:\/\/www.microsoft.com\/en-us\/haxtoolkit\/example\/neural-net-g11-f-example-based-explanations\/\",\"url\":\"https:\/\/www.microsoft.com\/en-us\/haxtoolkit\/example\/neural-net-g11-f-example-based-explanations\/\",\"name\":\"Image recognition | 11F: Example-based explanations - Microsoft HAX Toolkit\",\"isPartOf\":{\"@id\":\"https:\/\/www.microsoft.com\/en-us\/haxtoolkit\/#website\"},\"primaryImageOfPage\":{\"@id\":\"https:\/\/www.microsoft.com\/en-us\/haxtoolkit\/example\/neural-net-g11-f-example-based-explanations\/#primaryimage\"},\"image\":{\"@id\":\"https:\/\/www.microsoft.com\/en-us\/haxtoolkit\/example\/neural-net-g11-f-example-based-explanations\/#primaryimage\"},\"thumbnailUrl\":\"https:\/\/www.microsoft.com\/en-us\/haxtoolkit\/uploads\/prod\/2021\/05\/G11-F_Example-Based-Explanations_Google-Draw-annotated.png\",\"datePublished\":\"2021-05-27T16:44:53+00:00\",\"dateModified\":\"2023-05-26T12:07:19+00:00\",\"breadcrumb\":{\"@id\":\"https:\/\/www.microsoft.com\/en-us\/haxtoolkit\/example\/neural-net-g11-f-example-based-explanations\/#breadcrumb\"},\"inLanguage\":\"en-US\",\"potentialAction\":[{\"@type\":\"ReadAction\",\"target\":[\"https:\/\/www.microsoft.com\/en-us\/haxtoolkit\/example\/neural-net-g11-f-example-based-explanations\/\"]}]},{\"@type\":\"ImageObject\",\"inLanguage\":\"en-US\",\"@id\":\"https:\/\/www.microsoft.com\/en-us\/haxtoolkit\/example\/neural-net-g11-f-example-based-explanations\/#primaryimage\",\"url\":\"https:\/\/www.microsoft.com\/en-us\/haxtoolkit\/uploads\/prod\/2021\/05\/G11-F_Example-Based-Explanations_Google-Draw-annotated.png\",\"contentUrl\":\"https:\/\/www.microsoft.com\/en-us\/haxtoolkit\/uploads\/prod\/2021\/05\/G11-F_Example-Based-Explanations_Google-Draw-annotated.png\",\"width\":768,\"height\":954,\"caption\":\"Example-based explanations were used to explain how a neural net system recognizes an avocado from a drawing (Cai et al., 2019). In this case, the explanation shows drawings that taught the system what an avocado looks like.\"},{\"@type\":\"BreadcrumbList\",\"@id\":\"https:\/\/www.microsoft.com\/en-us\/haxtoolkit\/example\/neural-net-g11-f-example-based-explanations\/#breadcrumb\",\"itemListElement\":[{\"@type\":\"ListItem\",\"position\":1,\"name\":\"Home\",\"item\":\"https:\/\/www.microsoft.com\/en-us\/haxtoolkit\/\"},{\"@type\":\"ListItem\",\"position\":2,\"name\":\"G11: Make clear why the system did what it did.\",\"item\":\"https:\/\/www.microsoft.com\/en-us\/haxtoolkit\/guideline\/make-clear-why-the-system-did-what-it-did\/\"},{\"@type\":\"ListItem\",\"position\":3,\"name\":\"Image recognition | 11F: Example-based explanations\"}]},{\"@type\":\"WebSite\",\"@id\":\"https:\/\/www.microsoft.com\/en-us\/haxtoolkit\/#website\",\"url\":\"https:\/\/www.microsoft.com\/en-us\/haxtoolkit\/\",\"name\":\"Microsoft HAX Toolkit\",\"description\":\"Collaborative tools to help you create more effective and responsible human-AI experiences\",\"publisher\":{\"@id\":\"https:\/\/www.microsoft.com\/en-us\/haxtoolkit\/#organization\"},\"potentialAction\":[{\"@type\":\"SearchAction\",\"target\":{\"@type\":\"EntryPoint\",\"urlTemplate\":\"https:\/\/www.microsoft.com\/en-us\/haxtoolkit\/?s={search_term_string}\"},\"query-input\":{\"@type\":\"PropertyValueSpecification\",\"valueRequired\":true,\"valueName\":\"search_term_string\"}}],\"inLanguage\":\"en-US\"},{\"@type\":\"Organization\",\"@id\":\"https:\/\/www.microsoft.com\/en-us\/haxtoolkit\/#organization\",\"name\":\"Microsoft Corporation\",\"url\":\"https:\/\/www.microsoft.com\/en-us\/haxtoolkit\/\",\"logo\":{\"@type\":\"ImageObject\",\"inLanguage\":\"en-US\",\"@id\":\"https:\/\/www.microsoft.com\/en-us\/haxtoolkit\/#\/schema\/logo\/image\/\",\"url\":\"https:\/\/www.microsoft.com\/en-us\/haxtoolkit\/uploads\/prod\/2022\/07\/msft-logo.png\",\"contentUrl\":\"https:\/\/www.microsoft.com\/en-us\/haxtoolkit\/uploads\/prod\/2022\/07\/msft-logo.png\",\"width\":1536,\"height\":1536,\"caption\":\"Microsoft Corporation\"},\"image\":{\"@id\":\"https:\/\/www.microsoft.com\/en-us\/haxtoolkit\/#\/schema\/logo\/image\/\"}}]}<\/script>\n<!-- \/ Yoast SEO plugin. -->","yoast_head_json":{"title":"Image recognition | 11F: Example-based explanations - Microsoft HAX Toolkit","robots":{"index":"index","follow":"follow","max-snippet":"max-snippet:-1","max-image-preview":"max-image-preview:large","max-video-preview":"max-video-preview:-1"},"canonical":"https:\/\/www.microsoft.com\/en-us\/haxtoolkit\/example\/neural-net-g11-f-example-based-explanations\/","og_locale":"en_US","og_type":"article","og_title":"Image recognition | 11F: Example-based explanations - Microsoft HAX Toolkit","og_url":"https:\/\/www.microsoft.com\/en-us\/haxtoolkit\/example\/neural-net-g11-f-example-based-explanations\/","og_site_name":"Microsoft HAX Toolkit","article_modified_time":"2023-05-26T12:07:19+00:00","og_image":[{"width":768,"height":954,"url":"https:\/\/www.microsoft.com\/en-us\/haxtoolkit\/uploads\/prod\/2021\/05\/G11-F_Example-Based-Explanations_Google-Draw-annotated.png","type":"image\/png"}],"twitter_card":"summary_large_image","twitter_misc":{"Est. reading time":"1 minute","Written by":"Shipi Dhanorkar"},"schema":{"@context":"https:\/\/schema.org","@graph":[{"@type":"WebPage","@id":"https:\/\/www.microsoft.com\/en-us\/haxtoolkit\/example\/neural-net-g11-f-example-based-explanations\/","url":"https:\/\/www.microsoft.com\/en-us\/haxtoolkit\/example\/neural-net-g11-f-example-based-explanations\/","name":"Image recognition | 11F: Example-based explanations - Microsoft HAX Toolkit","isPartOf":{"@id":"https:\/\/www.microsoft.com\/en-us\/haxtoolkit\/#website"},"primaryImageOfPage":{"@id":"https:\/\/www.microsoft.com\/en-us\/haxtoolkit\/example\/neural-net-g11-f-example-based-explanations\/#primaryimage"},"image":{"@id":"https:\/\/www.microsoft.com\/en-us\/haxtoolkit\/example\/neural-net-g11-f-example-based-explanations\/#primaryimage"},"thumbnailUrl":"https:\/\/www.microsoft.com\/en-us\/haxtoolkit\/uploads\/prod\/2021\/05\/G11-F_Example-Based-Explanations_Google-Draw-annotated.png","datePublished":"2021-05-27T16:44:53+00:00","dateModified":"2023-05-26T12:07:19+00:00","breadcrumb":{"@id":"https:\/\/www.microsoft.com\/en-us\/haxtoolkit\/example\/neural-net-g11-f-example-based-explanations\/#breadcrumb"},"inLanguage":"en-US","potentialAction":[{"@type":"ReadAction","target":["https:\/\/www.microsoft.com\/en-us\/haxtoolkit\/example\/neural-net-g11-f-example-based-explanations\/"]}]},{"@type":"ImageObject","inLanguage":"en-US","@id":"https:\/\/www.microsoft.com\/en-us\/haxtoolkit\/example\/neural-net-g11-f-example-based-explanations\/#primaryimage","url":"https:\/\/www.microsoft.com\/en-us\/haxtoolkit\/uploads\/prod\/2021\/05\/G11-F_Example-Based-Explanations_Google-Draw-annotated.png","contentUrl":"https:\/\/www.microsoft.com\/en-us\/haxtoolkit\/uploads\/prod\/2021\/05\/G11-F_Example-Based-Explanations_Google-Draw-annotated.png","width":768,"height":954,"caption":"Example-based explanations were used to explain how a neural net system recognizes an avocado from a drawing (Cai et al., 2019). In this case, the explanation shows drawings that taught the system what an avocado looks like."},{"@type":"BreadcrumbList","@id":"https:\/\/www.microsoft.com\/en-us\/haxtoolkit\/example\/neural-net-g11-f-example-based-explanations\/#breadcrumb","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https:\/\/www.microsoft.com\/en-us\/haxtoolkit\/"},{"@type":"ListItem","position":2,"name":"G11: Make clear why the system did what it did.","item":"https:\/\/www.microsoft.com\/en-us\/haxtoolkit\/guideline\/make-clear-why-the-system-did-what-it-did\/"},{"@type":"ListItem","position":3,"name":"Image recognition | 11F: Example-based explanations"}]},{"@type":"WebSite","@id":"https:\/\/www.microsoft.com\/en-us\/haxtoolkit\/#website","url":"https:\/\/www.microsoft.com\/en-us\/haxtoolkit\/","name":"Microsoft HAX Toolkit","description":"Collaborative tools to help you create more effective and responsible human-AI experiences","publisher":{"@id":"https:\/\/www.microsoft.com\/en-us\/haxtoolkit\/#organization"},"potentialAction":[{"@type":"SearchAction","target":{"@type":"EntryPoint","urlTemplate":"https:\/\/www.microsoft.com\/en-us\/haxtoolkit\/?s={search_term_string}"},"query-input":{"@type":"PropertyValueSpecification","valueRequired":true,"valueName":"search_term_string"}}],"inLanguage":"en-US"},{"@type":"Organization","@id":"https:\/\/www.microsoft.com\/en-us\/haxtoolkit\/#organization","name":"Microsoft Corporation","url":"https:\/\/www.microsoft.com\/en-us\/haxtoolkit\/","logo":{"@type":"ImageObject","inLanguage":"en-US","@id":"https:\/\/www.microsoft.com\/en-us\/haxtoolkit\/#\/schema\/logo\/image\/","url":"https:\/\/www.microsoft.com\/en-us\/haxtoolkit\/uploads\/prod\/2022\/07\/msft-logo.png","contentUrl":"https:\/\/www.microsoft.com\/en-us\/haxtoolkit\/uploads\/prod\/2022\/07\/msft-logo.png","width":1536,"height":1536,"caption":"Microsoft Corporation"},"image":{"@id":"https:\/\/www.microsoft.com\/en-us\/haxtoolkit\/#\/schema\/logo\/image\/"}}]}},"_links":{"self":[{"href":"https:\/\/www.microsoft.com\/en-us\/haxtoolkit\/wp-json\/wp\/v2\/example\/1542"}],"collection":[{"href":"https:\/\/www.microsoft.com\/en-us\/haxtoolkit\/wp-json\/wp\/v2\/example"}],"about":[{"href":"https:\/\/www.microsoft.com\/en-us\/haxtoolkit\/wp-json\/wp\/v2\/types\/example"}],"version-history":[{"count":9,"href":"https:\/\/www.microsoft.com\/en-us\/haxtoolkit\/wp-json\/wp\/v2\/example\/1542\/revisions"}],"predecessor-version":[{"id":9657,"href":"https:\/\/www.microsoft.com\/en-us\/haxtoolkit\/wp-json\/wp\/v2\/example\/1542\/revisions\/9657"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/haxtoolkit\/wp-json\/wp\/v2\/media\/1359"}],"wp:attachment":[{"href":"https:\/\/www.microsoft.com\/en-us\/haxtoolkit\/wp-json\/wp\/v2\/media?parent=1542"}],"wp:term":[{"taxonomy":"application-type","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/haxtoolkit\/wp-json\/wp\/v2\/application-type?post=1542"},{"taxonomy":"goal","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/haxtoolkit\/wp-json\/wp\/v2\/goal?post=1542"},{"taxonomy":"guideline-term","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/haxtoolkit\/wp-json\/wp\/v2\/guideline-term?post=1542"},{"taxonomy":"product-category","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/haxtoolkit\/wp-json\/wp\/v2\/product-category?post=1542"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}