<?xml version="1.0" encoding="UTF-8"?><rss xmlns:dc="http://purl.org/dc/elements/1.1/" xmlns:content="http://purl.org/rss/1.0/modules/content/" xmlns:atom="http://www.w3.org/2005/Atom" version="2.0" xmlns:cc="http://cyber.law.harvard.edu/rss/creativeCommonsRssModule.html">
    <channel>
        <title><![CDATA[nDimensional - Medium]]></title>
        <description><![CDATA[I’m a healthcare data scientist and problem solver. Phd-ish in Applied Neuroscience. Family man. Hater of jargon. - Medium]]></description>
        <link>https://medium.com/ndimensional?source=rss----8a0afcb7e016---4</link>
        <image>
            <url>https://cdn-images-1.medium.com/proxy/1*TGH72Nnw24QL3iV9IOm4VA.png</url>
            <title>nDimensional - Medium</title>
            <link>https://medium.com/ndimensional?source=rss----8a0afcb7e016---4</link>
        </image>
        <generator>Medium</generator>
        <lastBuildDate>Thu, 19 Nov 2026 08:33:17 GMT</lastBuildDate>
        <atom:link href="https://medium.com/feed/ndimensional" rel="self" type="application/rss+xml"/>
        <webMaster><![CDATA[yourfriends@medium.com]]></webMaster>
        <atom:link href="http://medium.superfeedr.com/" rel="hub"/>
        <item>
            <title><![CDATA[How the “Not Hotdog” app from Silicon Valley forced me to try Neural Networks]]></title>
            <link>https://medium.com/ndimensional/how-the-not-hotdog-app-from-silicon-valley-forced-me-to-try-neural-networks-eb4186ff28ff?source=rss----8a0afcb7e016---4</link>
            <guid isPermaLink="false">https://medium.com/p/eb4186ff28ff</guid>
            <category><![CDATA[artificial-intelligence]]></category>
            <dc:creator><![CDATA[Mark Burghart]]></dc:creator>
            <pubDate>Tue, 23 Jan 2018 17:45:26 GMT</pubDate>
            <atom:updated>2018-01-23T17:45:25.818Z</atom:updated>
            <content:encoded><![CDATA[<p>To paraphrase ‘Mugatu’ from <em>Zoolander:</em></p><blockquote><em>“</em>Artificial Intelligence (AI) is so hot right now…”</blockquote><p>Machine/deep learning and AI are mentioned in nearly every meeting I attend. AI and deep learning have potential to revolutionize practically every industry, including healthcare, but I have some reservations. While AI is frequently discussed, few true applications of AI exist at scale.</p><p>Ahh… that might be a stretch. I guess I was looking for a truly impactful use…</p><p><strong>AND then came “Not Hotdog”</strong>. For those of you without a family member’s HBO GO log on, the “Not Hotdog” app was developed by Tim Anglade for HBO’s <em>Silicon Valley</em>. In the show, a programmer by the name of Jian-Yang decides to make an app that allows users to tell if objects are, or are not, hotdogs.</p><figure><img alt="" src="https://cdn-images-1.medium.com/max/650/1*ubJ-RF8CKGvjckDEICsxsQ.png" /><figcaption>Mr. Jian-Yang, lover of hotdog classification problems</figcaption></figure><p>While the use cases for such an app are fairly limiting (and thus, hilarious), Tim Anglade (a highly-skilled developer) decided to actually make the app for fans to try. Today, the app is available for <a href="https://play.google.com/store/apps/details?id=com.codylab.seefood&amp;hl=en">Android</a> and <a href="https://itunes.apple.com/us/app/not-hotdog/id1212457521?mt=8">iOS</a> and full details of the build are thankfully provided by <a href="https://medium.com/@timanglade/how-hbos-silicon-valley-built-not-hotdog-with-mobile-tensorflow-keras-react-native-ef03260747f3">Tim</a>.</p><figure><img alt="" src="https://cdn-images-1.medium.com/max/846/1*obzo5ChcEwCGUcq0hiYhrg.png" /><figcaption>The app in action</figcaption></figure><p>The performance of the app was quite impressive:</p><figure><img alt="" src="https://cdn-images-1.medium.com/max/1024/1*pYH6aVjo8J3cgtUndhb9tQ.jpeg" /><figcaption>Brats, squash, and buns couldn’t throw it off!</figcaption></figure><p>Although there were some pretty hilarious errors:</p><h3>David on Twitter</h3><p>If there&#39;s ketchup, it&#39;s a hotdog @FunnyAsianDude #nothotdog #NotHotdogchallenge</p><p>And reviews?! Oh, the reviews…</p><figure><img alt="" src="https://cdn-images-1.medium.com/max/878/1*pUswp52THlX0xCXiWma-Dw.png" /></figure><p>After reading Tim’s post (and watching the episode again), I got really excited to try using the app’s deep learning structure to address some imaging problems common in healthcare. One of the striking things that got me interested was the concept of using a pre-trained model, much like what <a href="http://www.fast.ai/">fast.ai</a> encourages. I loved this. My background isn’t in math or computer science. Sure, I know some, but my PhD isn’t in those subjects. I’m all about application. Applying the structure of the model to a new problem really intrigued me.</p><p>To be continued…</p><img src="https://medium.com/_/stat?event=post.clientViewed&referrerSource=full_rss&postId=eb4186ff28ff" width="1" height="1" alt=""><hr><p><a href="https://medium.com/ndimensional/how-the-not-hotdog-app-from-silicon-valley-forced-me-to-try-neural-networks-eb4186ff28ff">How the “Not Hotdog” app from Silicon Valley forced me to try Neural Networks</a> was originally published in <a href="https://medium.com/ndimensional">nDimensional</a> on Medium, where people are continuing the conversation by highlighting and responding to this story.</p>]]></content:encoded>
        </item>
    </channel>
</rss>