{"id":2484,"date":"2021-08-12T15:47:32","date_gmt":"2021-08-12T23:47:32","guid":{"rendered":"https:\/\/live-cometml.pantheonsite.io\/blog\/comet-newsletter-issue-13-ml-for-creative-user-interfaces-and-experiences-samples-from-our-ai-art-gallery-and-more\/"},"modified":"2021-08-12T15:47:32","modified_gmt":"2021-08-12T23:47:32","slug":"comet-newsletter-issue-13-ml-for-creative-user-interfaces-and-experiences-samples-from-our-ai-art-gallery-and-more","status":"publish","type":"post","link":"https:\/\/www.comet.com\/site\/blog\/comet-newsletter-issue-13-ml-for-creative-user-interfaces-and-experiences-samples-from-our-ai-art-gallery-and-more\/","title":{"rendered":"Issue 13: ML for Creative User Interfaces and Experiences, Samples from Our AI Art Gallery"},"content":{"rendered":"\n<h3 class=\"has-text-color wp-block-heading\" style=\"color: #747474;\"><em>A new Comet Industry Q&amp;A, a sampling of user submissions to our CLIPDraw public AI art gallery, and a few updates from around the ML industry<\/em><\/h3>\n\n\n\n<p>Welcome to issue #13 of The Comet Newsletter!\u00a0<\/p>\n\n\n\n<p>This week, we\u2019re excited to share <a href=\"https:\/\/comet-ml.zoom.us\/webinar\/register\/3016285407538\/WN_xG5hX2mSRXy4LmkSM3RqSA?utm_campaign=newsletter-13&amp;utm_source=blog-archive&amp;medium=frontmatter\">details about our next Industry Q&amp;A<\/a> exploring ML for creative UI\/UX\u2019s, as well as showcase some of our favorite pieces of AI-generated art from our recent CLIPDraw project (<a href=\"https:\/\/www.comet.com\/site\/clipdraw-gallery-ai-art-powered-by-comet-and-gradio\/?utm_campaign=newsletter-13&amp;utm_source=blog-archive&amp;utm_medium=frontmatter\">which you can read more about here<\/a>).<\/p>\n\n\n\n<p>Additionally, we jump back into the latest industry news\u2014<a href=\"https:\/\/www.microsoft.com\/en-us\/research\/blog\/make-every-feature-binary-a-135b-parameter-sparse-neural-network-for-massively-improved-search-relevance\/\">a 135 billion parameter model from Microsoft<\/a>, why we might need <a href=\"https:\/\/venturebeat.com\/2021\/08\/08\/to-create-agi-we-need-a-new-theory-of-intelligence\/\">a new theory of intelligence to achieve AGI<\/a>, and <a href=\"http:\/\/ai.googleblog.com\/2021\/08\/two-new-datasets-for-conversational-nlp.html\">two new datasets from Google for conversational NLP<\/a>.<\/p>\n\n\n\n<h3 class=\"wp-block-heading\">Like what you\u2019re reading? <a href=\"https:\/\/info.comet.ml\/newsletter-signup\/\">Subscribe here.<\/a><\/h3>\n\n\n\n<p>And be sure to follow us on <a href=\"https:\/\/twitter.com\/Cometml\">Twitter<\/a> and <a href=\"https:\/\/www.linkedin.com\/company\/comet-ml\/\">LinkedIn<\/a> \u2014 drop us a note if you have something we should cover in an upcoming issue!<\/p>\n\n\n\n<p>Happy Reading,<\/p>\n\n\n\n<p>Austin<\/p>\n\n\n\n<p>Head of Community, Comet<\/p>\n\n\n<center>&#8212;&#8212;&#8212;&#8212;&#8212;&#8212;&#8212;&#8212;&#8212;&#8212;&#8211;<\/center>\n\n\n<p><strong>FROM TEAM COMET<\/strong> | INDUSTRY | WHAT WE&#8217;RE READING | PROJECTS<\/p>\n\n\n\n<h2 class=\"wp-block-heading\"><a href=\"https:\/\/comet-ml.zoom.us\/webinar\/register\/3016285407538\/WN_xG5hX2mSRXy4LmkSM3RqSA\">Upcoming Industry Q&amp;A: Building Creative User Interfaces and Experiences with Machine Learning<\/a><\/h2>\n\n\n\n<p>&nbsp;<\/p>\n\n\n\n<div class=\"wp-block-image\">\n<figure class=\"aligncenter size-large is-resized\"><img loading=\"lazy\" decoding=\"async\" class=\"wp-image-6255\" src=\"https:\/\/www.comet.com\/site\/wp-content\/uploads\/2022\/06\/full-asset-1-1024x535.png\" alt=\"\" width=\"768\" height=\"401\" \/><\/figure>\n<\/div>\n\n\n\n<p>&nbsp;<\/p>\n\n\n\n<blockquote class=\"wp-block-quote has-text-align-left is-layout-flow wp-block-quote-is-layout-flow\">\n<p><a href=\"https:\/\/comet-ml.zoom.us\/webinar\/register\/3016285407538\/WN_xG5hX2mSRXy4LmkSM3RqSA?utm_campaign=industryqa-ux-ml&amp;utm_source=blog-archive&amp;medium=newsletter-pull-quote\"><strong>Register for the event here!<\/strong><\/a><\/p>\n<\/blockquote>\n\n\n\n<p>We&#8217;re really excited to share information about <a href=\"https:\/\/comet-ml.zoom.us\/webinar\/register\/3016285407538\/WN_xG5hX2mSRXy4LmkSM3RqSA?utm_campaign=industryqa-ux-ml&amp;utm_source=blog-archive&amp;medium=newsletter-item\">our next Industry Q&amp;A<\/a>, especially after how much we (and hopefully you!) enjoyed our July event on collaborative DS\/ML\u2014ICYMI, you can <a href=\"https:\/\/youtube.com\/playlist?list=PLX9GmL8cVn_wQCkhb4ARSFoJ5ZgtuISPF\">watch that full event + highlights on this YouTube playlist<\/a>.<\/p>\n\n\n\n<p>This month, we&#8217;ll be chatting with <a href=\"https:\/\/twitter.com\/2020cv_inc\">Hart Woolery<\/a> of <a href=\"https:\/\/www.2020cv.com\/\">2020CV<\/a> and <a href=\"https:\/\/victordibia.com\/\">Victor Dibia<\/a> of <a href=\"https:\/\/www.cloudera.com\/products\/fast-forward-labs-research.html\">Cloudera Fast Forward Labs<\/a>, two industry leaders at the forefront of building creative and immersive user interfaces and experiences that are powered by machine learning.<\/p>\n\n\n\n<p>For more complete information, check out our full blog post preview. But here are the main details you need to know:<\/p>\n\n\n\n<ul class=\"wp-block-list\">\n<li><strong>Event theme:<\/strong> Building Creative User Interfaces and Experiences with Machine Learning<\/li>\n<li><strong>Event date + time:<\/strong> Tuesday, August 24th, 1pm &#8211; 2pm ET (10am &#8211; 11am PT)<\/li>\n<li><strong>Registration:<\/strong> You can <a href=\"https:\/\/comet-ml.zoom.us\/webinar\/register\/3016285407538\/WN_xG5hX2mSRXy4LmkSM3RqSA?utm_campaign=industryqa-ux-ml&amp;utm_source=blog-archive&amp;medium=newsletter-registration-info\">register for this virtual event for free!<\/a> We&#8217;ll also share links to the session and various highlights with those who register<\/li>\n<\/ul>\n\n\n\n<p>We hope to see you at this and future events! And be sure to bring your questions for Hart and Victor, as we&#8217;ll save some time at the end for audience questions.<\/p>\n\n\n\n<h3 class=\"wp-block-heading\"><em><a href=\"https:\/\/comet-ml.zoom.us\/webinar\/register\/3016285407538\/WN_xG5hX2mSRXy4LmkSM3RqSA?utm_campaign=industryqa-ux-ml&amp;utm_source=blog-archive&amp;medium=newsletter-h3\">Save your seat<\/a><\/em><\/h3>\n\n\n\n<p>&nbsp;<\/p>\n\n\n\n<h2 class=\"wp-block-heading\">Samples from Comet&#8217;s AI art gallery, powered by CLIPDraw and Gradio<\/h2>\n\n\n\n<p>&nbsp;<\/p>\n\n\n\n<div class=\"wp-block-image\">\n<figure class=\"aligncenter size-large is-resized\"><img loading=\"lazy\" decoding=\"async\" class=\"wp-image-6232\" src=\"https:\/\/www.comet.com\/site\/wp-content\/uploads\/2022\/06\/team-comet-ml-clipdraw-cover-1024x476.png\" alt=\"\" width=\"768\" height=\"357\" \/><\/figure>\n<\/div>\n\n\n\n<p>&nbsp;<\/p>\n\n\n\n<p>Last week, <a href=\"https:\/\/clipdraw.comet.ml\/?utm_campaign=newsletter-12&amp;utm_source=blog-archive&amp;utm_medium=newsletter-item\">we shared a fun project<\/a> that we hoped would allow us to build and showcase a community-generated art gallery by combining the powers of a generative art model (CLIPDraw), <a href=\"http:\/\/gradio.app\">Gradio&#8217;s<\/a> model testing UI, and Comet&#8217;s experiment management capabilities.<\/p>\n\n\n\n<p>As of the writing of this newsletter, we&#8217;re up to more than 900 community submissions! So first, thank you for your support in turning this fun idea into a legitimate shared AI art project.<\/p>\n\n\n\n<p>Second, we wanted to share a few of our favorite and most unique submissions from the bunch (see below and <a href=\"https:\/\/twitter.com\/Cometml\/status\/1425815016012455939\">check out our thread on Twitter<\/a>). If you&#8217;ve created something you like, let us know! Tag us on Twitter, reply to this email, or find me on LinkedIn\u2014we&#8217;d love to share your creations with the community.<\/p>\n\n\n\n<p>In case you missed this project last week, not to worry! Here are a few links to help you jump right in:<\/p>\n\n\n\n<ul class=\"wp-block-list\">\n<li><a href=\"https:\/\/www.comet.com\/site\/clipdraw-gallery-ai-art-powered-by-comet-and-gradio?utm_campaign=newsletter-12&amp;utm_source-blog-archive&amp;utm_medium=resources-list\">Our Full Blog Post<\/a><\/li>\n<li><a href=\"https:\/\/clipdraw.comet.ml\/?utm_campaign=newsletter-12&amp;utm_source=blog-archive&amp;utm_medium=resources-list\">Project Interface<\/a><\/li>\n<li><a href=\"https:\/\/www.comet.com\/team-comet-ml\/clipdraw\/view\/Y4aT3gy6IrPQKBi5wncFXCYLR?utm_campaign=newsletter-12&amp;utm_source=blog-archive&amp;utm_medium=resources-list\">Public Comet Project<\/a> (with all submitted prompts)<\/li>\n<li><a href=\"https:\/\/colab.research.google.com\/drive\/16nR8_Ida5tID1RSzLy1Fv_LLav3MF1Zt\">Colab Notebook Example<\/a><\/li>\n<\/ul>\n\n\n\n<p>&nbsp;<\/p>\n\n\n\n<figure class=\"wp-block-gallery aligncenter has-nested-images columns-default is-cropped wp-block-gallery-1 is-layout-flex wp-block-gallery-is-layout-flex\">\n<figure class=\"wp-block-image size-large\"><img decoding=\"async\" data-id=\"6270\" class=\"wp-image-6270\" src=\"https:\/\/www.comet.com\/site\/wp-content\/uploads\/2022\/06\/0_The-whole-worlds-a-stage-1.gif\" alt=\"\" \/>\n<figcaption><a href=\"https:\/\/www.comet.com\/team-comet-ml\/clipdraw\/8f124a2a89a0414c97d3e6c2618c0820?experiment-tab=images\">The whole world&#8217;s a stage<\/a><\/figcaption>\n<\/figure>\n\n\n\n<figure class=\"wp-block-image size-large\"><img decoding=\"async\" data-id=\"6271\" class=\"wp-image-6271\" src=\"https:\/\/www.comet.com\/site\/wp-content\/uploads\/2022\/06\/0_Dogs-dressed-as-wizards-1.gif\" alt=\"\" \/>\n<figcaption><a href=\"https:\/\/www.comet.com\/team-comet-ml\/clipdraw\/7c7edb0d5a8c473e9d551594c542b6f1?experiment-tab=images\">Dogs dressed as wizards<\/a><\/figcaption>\n<\/figure>\n\n\n\n<figure class=\"wp-block-image size-large\"><img decoding=\"async\" data-id=\"6273\" class=\"wp-image-6273\" src=\"https:\/\/www.comet.com\/site\/wp-content\/uploads\/2022\/06\/0_barack-obama-in-mario-kart-1.gif\" alt=\"\" \/>\n<figcaption><a href=\"https:\/\/www.comet.com\/team-comet-ml\/clipdraw\/50ed94b75e5f4feb96747caa494308a7?experiment-tab=images\">Barack Obama in Mario Kart<\/a><\/figcaption>\n<\/figure>\n\n\n\n<figure class=\"wp-block-image size-large\"><img decoding=\"async\" data-id=\"6272\" class=\"wp-image-6272\" src=\"https:\/\/www.comet.com\/site\/wp-content\/uploads\/2022\/06\/0_cat-muffin-1.gif\" alt=\"\" \/>\n<figcaption><a href=\"https:\/\/www.comet.com\/team-comet-ml\/clipdraw\/11e14ab84a54483797b2fb9c3813271d?experiment-tab=images\">Cat muffin<\/a><\/figcaption>\n<\/figure>\n<\/figure>\n\n\n\n<p>&nbsp;<\/p>\n\n\n<center>&#8212;&#8212;&#8212;&#8212;&#8212;&#8212;&#8212;&#8212;&#8212;&#8212;&#8211;<\/center>\n\n\n<p>FROM TEAM COMET | <strong>INDUSTRY<\/strong> | WHAT WE&#8217;RE READING | PROJECTS | PERSPECTIVE<\/p>\n\n\n\n<h2 class=\"wp-block-heading\"><a href=\"https:\/\/www.microsoft.com\/en-us\/research\/blog\/make-every-feature-binary-a-135b-parameter-sparse-neural-network-for-massively-improved-search-relevance\/\">Microsoft AI researchers introduced a 135 billion-parameter neural net and deployed it on Bing to improve search results<\/a><\/h2>\n\n\n\n<p>&nbsp;<\/p>\n\n\n\n<div class=\"wp-block-image\">\n<figure class=\"aligncenter size-large is-resized\"><img loading=\"lazy\" decoding=\"async\" class=\"wp-image-6247\" src=\"https:\/\/www.comet.com\/site\/wp-content\/uploads\/2022\/06\/MEB.jpeg\" alt=\"\" width=\"768\" height=\"432\" \/>\n<figcaption><em><a href=\"https:\/\/www.microsoft.com\/en-us\/research\/blog\/make-every-feature-binary-a-135b-parameter-sparse-neural-network-for-massively-improved-search-relevance\/\">Image Source<\/a><\/em><\/figcaption>\n<\/figure>\n<\/div>\n\n\n\n<p>&nbsp;<\/p>\n\n\n\n<p>Microsoft is calling the project &#8220;MEB&#8221;, which stands for &#8220;Make Every Feature Binary&#8221;, and is designed with the intention of pushing language understanding beyond semantic relationships\u2014an important part of helping search engines more effectively match queries with target documents and webpages.<\/p>\n\n\n\n<p>At 135bn parameters, it&#8217;s not the biggest neural network we&#8217;ve seen (that honor goes to OpenAI&#8217;s famous GPT-3, at 175bn), but MEB does have a few unique properties that differentiate it from other large language models.<\/p>\n\n\n\n<p>Specifically, MEB can map single features, meaning that it&#8217;s less likely to overgeneralize, and can take a fill-in-the-blank problem (i.e. &#8220;____ can fly&#8221;) and create a feature map that includes many possibilities, not just the one that might be the most obvious (&#8220;birds&#8221;).<\/p>\n\n\n\n<p>The researchers at Microsoft behind this effort explain this process well, noting that &#8220;MEB&#8230;can assign weights that distinguish between the ability to fly in, say, a penguin and a puffin. It can do this for each of the characteristics that make a bird\u2014or any entity or object for that matter\u2014singular. Instead of saying \u201cbirds can fly,\u201d MEB paired with Transformer models can take this to another level of classification, saying \u201cbirds can fly, except ostriches, penguins, and these other birds.\u201d<\/p>\n\n\n\n<p>According to the Microsoft team, Bing has also seen some tangible improvements from this effort, including a (nearly) 2% increase in clickthrough rate on top search results, and a more than 1% reduction in query reformulation (i.e. users having to reshape an original query because of unhelpful results).<\/p>\n\n\n\n<p><a href=\"https:\/\/www.microsoft.com\/en-us\/research\/blog\/make-every-feature-binary-a-135b-parameter-sparse-neural-network-for-massively-improved-search-relevance\/\">Read Microsoft&#8217;s full blog post here<\/a><\/p>\n\n\n<center>&#8212;&#8212;&#8212;&#8212;&#8212;&#8212;&#8212;&#8212;&#8212;&#8212;&#8211;<\/center>\n\n\n<p>FROM TEAM COMET | INDUSTRY | <strong>WHAT WE&#8217;RE READING<\/strong> | PROJECTS | PERSPECTIVE<\/p>\n\n\n\n<h2 class=\"wp-block-heading\"><a href=\"https:\/\/venturebeat.com\/2021\/08\/08\/to-create-agi-we-need-a-new-theory-of-intelligence\/\">To create AGI, we need a new theory of intelligence<\/a><\/h2>\n\n\n\n<p>&nbsp;<\/p>\n\n\n\n<div class=\"wp-block-image\">\n<figure class=\"aligncenter size-large is-resized\"><img loading=\"lazy\" decoding=\"async\" class=\"wp-image-6253\" src=\"https:\/\/www.comet.com\/site\/wp-content\/uploads\/2022\/06\/agi-1024x512.jpeg\" alt=\"\" width=\"768\" height=\"384\" \/>\n<figcaption><a href=\"https:\/\/venturebeat.com\/2021\/08\/08\/to-create-agi-we-need-a-new-theory-of-intelligence\/\"><em>Image Source<\/em><\/a><\/figcaption>\n<\/figure>\n<\/div>\n\n\n\n<p>&nbsp;<\/p>\n\n\n\n<p>If you&#8217;ve ever watched or read general interest science fiction about AI, then you might know that the &#8220;holy grail&#8221; of the technology is AGI, or Artificial General Intelligence\u2014the threshold at which computers can act and think like humans.<\/p>\n\n\n\n<p>But the pursuit has served as an ongoing enigma for researchers and scientists. Ben Dickson, writing for VentureBeat, explores some of the barriers to AGI through the lens of new research on the &#8220;considered response theory,&#8221; from Sathyanaraya Raghavachary, Associate Professor of Computer Science at the University of Southern California.<\/p>\n\n\n\n<p>Essentially, Raghavachary argues that life and levels of intelligence are composed of structures that consider and produce responses, &#8220;meant to [help] an agent survive and reproduce in its environment by interacting with it appropriately.&#8221;<\/p>\n\n\n\n<p>This conception of intelligence is quite a bit different from the processes underlying most AI systems, and our assumptions about how machine intelligence works\u2014mechanisms and principles like reason, planning, goal-seeking, and more.<\/p>\n\n\n\n<p>Furthermore, biological intelligence is &#8220;embodied&#8221;, meaning there are direct and inextricable connections between &#8220;mind&#8221; and body&#8221; that today&#8217;s AI systems are unable to replicate.<\/p>\n\n\n\n<p><a href=\"https:\/\/venturebeat.com\/2021\/08\/08\/to-create-agi-we-need-a-new-theory-of-intelligence\/\">Read the full report in VentureBeat.<\/a><\/p>\n\n\n<center>&#8212;&#8212;&#8212;&#8212;&#8212;&#8212;&#8212;&#8212;&#8212;&#8212;&#8211;<\/center>\n\n\n<p>FROM TEAM COMET | INDUSTRY | WHAT WE&#8217;RE READING | <strong>PROJECTS<\/strong><\/p>\n\n\n\n<h2 class=\"wp-block-heading\"><a href=\"http:\/\/ai.googleblog.com\/2021\/08\/two-new-datasets-for-conversational-nlp.html\">Two New Datasets for Conversational NLP: TimeDial and Disfl-QA<\/a><\/h2>\n\n\n\n<p>&nbsp;<\/p>\n\n\n\n<div class=\"wp-block-image\">\n<figure class=\"aligncenter size-large is-resized\"><img loading=\"lazy\" decoding=\"async\" class=\"wp-image-6254\" src=\"https:\/\/www.comet.com\/site\/wp-content\/uploads\/2022\/06\/brandon-romanchuk-AkCpJd6R2QU-unsplash-scaled.jpg\" alt=\"\" width=\"768\" height=\"510\" \/>\n<figcaption><a href=\"https:\/\/unsplash.com\/photos\/AkCpJd6R2QU\"><em>Image Source<\/em><\/a><\/figcaption>\n<\/figure>\n<\/div>\n\n\n\n<p>&nbsp;<\/p>\n\n\n\n<p>Last week, Google introduced two new datasets for conversational AI systems: &#8220;<a href=\"https:\/\/arxiv.org\/abs\/2106.04571\">TimeDial<\/a>, for temporal commonsense reasoning in dialog, and\u00a0<a href=\"https:\/\/arxiv.org\/abs\/2106.04016\">Disfl-QA<\/a>, which focuses on contextual disfluencies.&#8221;<\/p>\n\n\n\n<p>Much like the problem Microsoft was looking to solve with MEB (see above), conversational agents struggle with fill-in-the-blank scenarios, especially when those blanks assume certain temporal inter-dependencies and reasoning that might seem obvious to humans. TimeDial consists of roughly 1,500 dialogues that are presented in multiple choice format with options that represent one temporal span. The model is then asked to select all &#8220;correct&#8221; answers among the 4 options.<\/p>\n\n\n\n<p>Disfl-QA is aimed at solving issues that conversational agents have with disfluency (interruptions in regular speech flows, i.e. &#8220;When is Lent, I mean, Easter, this year?&#8221;), typically in speech recognition systems. Disfl-QA is the first dataset that&#8217;s targeted specifically at these kinds of speech irregularities, making it an incredibly important data source for training more performant speech recognition systems.<\/p>\n\n\n\n<p><a href=\"https:\/\/ai.googleblog.com\/2021\/08\/two-new-datasets-for-conversational-nlp.html\">Read more about these new datasets on Google&#8217;s AI blog.<\/a><\/p>\n","protected":false},"excerpt":{"rendered":"<p>A new Comet Industry Q&#038;A, a sampling of user submissions to our CLIPDraw public AI art gallery, and a few updates from around the ML industry<\/p>\n","protected":false},"author":1,"featured_media":2304,"comment_status":"closed","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"customer_name":"","customer_description":"","customer_industry":"","customer_technologies":"","customer_logo":"","footnotes":""},"categories":[10],"tags":[],"coauthors":[130],"class_list":["post-2484","post","type-post","status-publish","format-standard","has-post-thumbnail","hentry","category-industry"],"yoast_head":"<!-- This site is optimized with the Yoast SEO Premium plugin v25.9 (Yoast SEO v25.9) - https:\/\/yoast.com\/wordpress\/plugins\/seo\/ -->\n<title>Issue 13: ML for Creative User Interfaces and Experiences, Samples from Our AI Art Gallery - Comet<\/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.comet.com\/site\/blog\/comet-newsletter-issue-13-ml-for-creative-user-interfaces-and-experiences-samples-from-our-ai-art-gallery-and-more\/\" \/>\n<meta property=\"og:locale\" content=\"en_US\" \/>\n<meta property=\"og:type\" content=\"article\" \/>\n<meta property=\"og:title\" content=\"Issue 13: ML for Creative User Interfaces and Experiences, Samples from Our AI Art Gallery\" \/>\n<meta property=\"og:description\" content=\"A new Comet Industry Q&amp;A, a sampling of user submissions to our CLIPDraw public AI art gallery, and a few updates from around the ML industry\" \/>\n<meta property=\"og:url\" content=\"https:\/\/www.comet.com\/site\/blog\/comet-newsletter-issue-13-ml-for-creative-user-interfaces-and-experiences-samples-from-our-ai-art-gallery-and-more\/\" \/>\n<meta property=\"og:site_name\" content=\"Comet\" \/>\n<meta property=\"article:publisher\" content=\"https:\/\/www.facebook.com\/cometdotml\" \/>\n<meta property=\"article:published_time\" content=\"2021-08-12T23:47:32+00:00\" \/>\n<meta property=\"og:image\" content=\"https:\/\/www.comet.com\/site\/wp-content\/uploads\/2022\/06\/Comet-Newsletter-Ad-1200x627-02.jpg\" \/>\n\t<meta property=\"og:image:width\" content=\"1200\" \/>\n\t<meta property=\"og:image:height\" content=\"627\" \/>\n\t<meta property=\"og:image:type\" content=\"image\/jpeg\" \/>\n<meta name=\"author\" content=\"Austin Kodra\" \/>\n<meta name=\"twitter:card\" content=\"summary_large_image\" \/>\n<meta name=\"twitter:creator\" content=\"@Cometml\" \/>\n<meta name=\"twitter:site\" content=\"@Cometml\" \/>\n<meta name=\"twitter:label1\" content=\"Written by\" \/>\n\t<meta name=\"twitter:data1\" content=\"Austin Kodra\" \/>\n\t<meta name=\"twitter:label2\" content=\"Est. reading time\" \/>\n\t<meta name=\"twitter:data2\" content=\"8 minutes\" \/>\n<!-- \/ Yoast SEO Premium plugin. -->","yoast_head_json":{"title":"Issue 13: ML for Creative User Interfaces and Experiences, Samples from Our AI Art Gallery - Comet","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.comet.com\/site\/blog\/comet-newsletter-issue-13-ml-for-creative-user-interfaces-and-experiences-samples-from-our-ai-art-gallery-and-more\/","og_locale":"en_US","og_type":"article","og_title":"Issue 13: ML for Creative User Interfaces and Experiences, Samples from Our AI Art Gallery","og_description":"A new Comet Industry Q&A, a sampling of user submissions to our CLIPDraw public AI art gallery, and a few updates from around the ML industry","og_url":"https:\/\/www.comet.com\/site\/blog\/comet-newsletter-issue-13-ml-for-creative-user-interfaces-and-experiences-samples-from-our-ai-art-gallery-and-more\/","og_site_name":"Comet","article_publisher":"https:\/\/www.facebook.com\/cometdotml","article_published_time":"2021-08-12T23:47:32+00:00","og_image":[{"width":1200,"height":627,"url":"https:\/\/www.comet.com\/site\/wp-content\/uploads\/2022\/06\/Comet-Newsletter-Ad-1200x627-02.jpg","type":"image\/jpeg"}],"author":"Austin Kodra","twitter_card":"summary_large_image","twitter_creator":"@Cometml","twitter_site":"@Cometml","twitter_misc":{"Written by":"Austin Kodra","Est. reading time":"8 minutes"},"schema":{"@context":"https:\/\/schema.org","@graph":[{"@type":"Article","@id":"https:\/\/www.comet.com\/site\/blog\/comet-newsletter-issue-13-ml-for-creative-user-interfaces-and-experiences-samples-from-our-ai-art-gallery-and-more\/#article","isPartOf":{"@id":"https:\/\/www.comet.com\/site\/blog\/comet-newsletter-issue-13-ml-for-creative-user-interfaces-and-experiences-samples-from-our-ai-art-gallery-and-more\/"},"author":{"name":"engineering@atre.net","@id":"https:\/\/www.comet.com\/site\/#\/schema\/person\/550ac35e8e821db8064c5bd1f0a04e6b"},"headline":"Issue 13: ML for Creative User Interfaces and Experiences, Samples from Our AI Art Gallery","datePublished":"2021-08-12T23:47:32+00:00","mainEntityOfPage":{"@id":"https:\/\/www.comet.com\/site\/blog\/comet-newsletter-issue-13-ml-for-creative-user-interfaces-and-experiences-samples-from-our-ai-art-gallery-and-more\/"},"wordCount":1292,"publisher":{"@id":"https:\/\/www.comet.com\/site\/#organization"},"image":{"@id":"https:\/\/www.comet.com\/site\/blog\/comet-newsletter-issue-13-ml-for-creative-user-interfaces-and-experiences-samples-from-our-ai-art-gallery-and-more\/#primaryimage"},"thumbnailUrl":"https:\/\/www.comet.com\/site\/wp-content\/uploads\/2022\/06\/Comet-Newsletter-Ad-1200x627-02.jpg","articleSection":["Industry"],"inLanguage":"en-US"},{"@type":"WebPage","@id":"https:\/\/www.comet.com\/site\/blog\/comet-newsletter-issue-13-ml-for-creative-user-interfaces-and-experiences-samples-from-our-ai-art-gallery-and-more\/","url":"https:\/\/www.comet.com\/site\/blog\/comet-newsletter-issue-13-ml-for-creative-user-interfaces-and-experiences-samples-from-our-ai-art-gallery-and-more\/","name":"Issue 13: ML for Creative User Interfaces and Experiences, Samples from Our AI Art Gallery - Comet","isPartOf":{"@id":"https:\/\/www.comet.com\/site\/#website"},"primaryImageOfPage":{"@id":"https:\/\/www.comet.com\/site\/blog\/comet-newsletter-issue-13-ml-for-creative-user-interfaces-and-experiences-samples-from-our-ai-art-gallery-and-more\/#primaryimage"},"image":{"@id":"https:\/\/www.comet.com\/site\/blog\/comet-newsletter-issue-13-ml-for-creative-user-interfaces-and-experiences-samples-from-our-ai-art-gallery-and-more\/#primaryimage"},"thumbnailUrl":"https:\/\/www.comet.com\/site\/wp-content\/uploads\/2022\/06\/Comet-Newsletter-Ad-1200x627-02.jpg","datePublished":"2021-08-12T23:47:32+00:00","breadcrumb":{"@id":"https:\/\/www.comet.com\/site\/blog\/comet-newsletter-issue-13-ml-for-creative-user-interfaces-and-experiences-samples-from-our-ai-art-gallery-and-more\/#breadcrumb"},"inLanguage":"en-US","potentialAction":[{"@type":"ReadAction","target":["https:\/\/www.comet.com\/site\/blog\/comet-newsletter-issue-13-ml-for-creative-user-interfaces-and-experiences-samples-from-our-ai-art-gallery-and-more\/"]}]},{"@type":"ImageObject","inLanguage":"en-US","@id":"https:\/\/www.comet.com\/site\/blog\/comet-newsletter-issue-13-ml-for-creative-user-interfaces-and-experiences-samples-from-our-ai-art-gallery-and-more\/#primaryimage","url":"https:\/\/www.comet.com\/site\/wp-content\/uploads\/2022\/06\/Comet-Newsletter-Ad-1200x627-02.jpg","contentUrl":"https:\/\/www.comet.com\/site\/wp-content\/uploads\/2022\/06\/Comet-Newsletter-Ad-1200x627-02.jpg","width":1200,"height":627,"caption":"Comet Newsletter"},{"@type":"BreadcrumbList","@id":"https:\/\/www.comet.com\/site\/blog\/comet-newsletter-issue-13-ml-for-creative-user-interfaces-and-experiences-samples-from-our-ai-art-gallery-and-more\/#breadcrumb","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https:\/\/www.comet.com\/site\/"},{"@type":"ListItem","position":2,"name":"Issue 13: ML for Creative User Interfaces and Experiences, Samples from Our AI Art Gallery"}]},{"@type":"WebSite","@id":"https:\/\/www.comet.com\/site\/#website","url":"https:\/\/www.comet.com\/site\/","name":"Comet","description":"Build Better Models Faster","publisher":{"@id":"https:\/\/www.comet.com\/site\/#organization"},"potentialAction":[{"@type":"SearchAction","target":{"@type":"EntryPoint","urlTemplate":"https:\/\/www.comet.com\/site\/?s={search_term_string}"},"query-input":{"@type":"PropertyValueSpecification","valueRequired":true,"valueName":"search_term_string"}}],"inLanguage":"en-US"},{"@type":"Organization","@id":"https:\/\/www.comet.com\/site\/#organization","name":"Comet ML, Inc.","alternateName":"Comet","url":"https:\/\/www.comet.com\/site\/","logo":{"@type":"ImageObject","inLanguage":"en-US","@id":"https:\/\/www.comet.com\/site\/#\/schema\/logo\/image\/","url":"https:\/\/www.comet.com\/site\/wp-content\/uploads\/2025\/01\/logo_comet_square.png","contentUrl":"https:\/\/www.comet.com\/site\/wp-content\/uploads\/2025\/01\/logo_comet_square.png","width":310,"height":310,"caption":"Comet ML, Inc."},"image":{"@id":"https:\/\/www.comet.com\/site\/#\/schema\/logo\/image\/"},"sameAs":["https:\/\/www.facebook.com\/cometdotml","https:\/\/x.com\/Cometml","https:\/\/www.youtube.com\/channel\/UCmN63HKvfXSCS-UwVwmK8Hw"]},{"@type":"Person","@id":"https:\/\/www.comet.com\/site\/#\/schema\/person\/550ac35e8e821db8064c5bd1f0a04e6b","name":"engineering@atre.net","image":{"@type":"ImageObject","inLanguage":"en-US","@id":"https:\/\/www.comet.com\/site\/#\/schema\/person\/image\/027c18177377edf459980f0cfb83706c","url":"https:\/\/secure.gravatar.com\/avatar\/d002a459a297e0d1779329318029aee19868c312b3e1f3c9ec9b3e3add2740de?s=96&d=mm&r=g","contentUrl":"https:\/\/secure.gravatar.com\/avatar\/d002a459a297e0d1779329318029aee19868c312b3e1f3c9ec9b3e3add2740de?s=96&d=mm&r=g","caption":"engineering@atre.net"},"sameAs":["https:\/\/live-cometml.pantheonsite.io"],"url":"https:\/\/www.comet.com\/site\/blog\/author\/engineeringatre-net\/"}]}},"_links":{"self":[{"href":"https:\/\/www.comet.com\/site\/wp-json\/wp\/v2\/posts\/2484","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/www.comet.com\/site\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/www.comet.com\/site\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/www.comet.com\/site\/wp-json\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/www.comet.com\/site\/wp-json\/wp\/v2\/comments?post=2484"}],"version-history":[{"count":0,"href":"https:\/\/www.comet.com\/site\/wp-json\/wp\/v2\/posts\/2484\/revisions"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/www.comet.com\/site\/wp-json\/wp\/v2\/media\/2304"}],"wp:attachment":[{"href":"https:\/\/www.comet.com\/site\/wp-json\/wp\/v2\/media?parent=2484"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/www.comet.com\/site\/wp-json\/wp\/v2\/categories?post=2484"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/www.comet.com\/site\/wp-json\/wp\/v2\/tags?post=2484"},{"taxonomy":"author","embeddable":true,"href":"https:\/\/www.comet.com\/site\/wp-json\/wp\/v2\/coauthors?post=2484"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}