<?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[LMDL - Medium]]></title>
        <description><![CDATA[Learning Machine and Deep Learning - Medium]]></description>
        <link>https://medium.com/lmdl?source=rss----d1d153c494af---4</link>
        <image>
            <url>https://cdn-images-1.medium.com/proxy/1*TGH72Nnw24QL3iV9IOm4VA.png</url>
            <title>LMDL - Medium</title>
            <link>https://medium.com/lmdl?source=rss----d1d153c494af---4</link>
        </image>
        <generator>Medium</generator>
        <lastBuildDate>Wed, 18 Nov 2026 17:21:21 GMT</lastBuildDate>
        <atom:link href="https://medium.com/feed/lmdl" rel="self" type="application/rss+xml"/>
        <webMaster><![CDATA[yourfriends@medium.com]]></webMaster>
        <atom:link href="http://medium.superfeedr.com/" rel="hub"/>
        <item>
            <title><![CDATA[PyTorch Scholarship Challenge from Facebook]]></title>
            <link>https://medium.com/lmdl/pytorch-scholarship-challenge-from-facebook-a9d41733b4b4?source=rss----d1d153c494af---4</link>
            <guid isPermaLink="false">https://medium.com/p/a9d41733b4b4</guid>
            <category><![CDATA[udacity]]></category>
            <category><![CDATA[deep-learning]]></category>
            <category><![CDATA[pytorch]]></category>
            <category><![CDATA[facebook]]></category>
            <category><![CDATA[scholarship]]></category>
            <dc:creator><![CDATA[Aadam]]></dc:creator>
            <pubDate>Thu, 31 Jan 2019 18:59:16 GMT</pubDate>
            <atom:updated>2019-01-31T18:59:16.567Z</atom:updated>
            <content:encoded><![CDATA[<figure><img alt="" src="https://cdn-images-1.medium.com/max/768/1*RmLNJSpOBNA8MW6cPr4B3Q.png" /></figure><p>I got accepted into the PyTorch Scholarship Challenge program, offered by Facebook, which focuses on teaching Deep Learning using the PyTorch framework.</p><p>There were two phases of this challenge. In Phase 1, they selected about 10,000 students worldwide to participate in the challenge. Out of those 10,000 students, only 300 would be selected for Phase 2, in which they’d have access to the complete Deep Learning Nanodegree for free.</p><p>As I was planning to learn the Pytorch framework and was looking for some amazing tutorials to get started, naturally I was very excited when I got selected into the Pytorch Scholarship Challenge Phase 1. My previous experience with Udacity’s Nanodegree programs was very rewarding in which I completed 3 Nanodegree programs, namely Machine Learning Engineer, Android Basics and Android Developer. But that was before they changed their pricing model, from monthly subscription to a one-time up-front payment system. After that, they also changed their teaching methods somewhat and instead of self-paced learning, they turned these Nanodegree programs into a schedule-based class type program. I wasn’t sure if I’d enjoy this as much, but I did, a lot.</p><p>The video content of the program was absolutely amazing, as always. The production quality, the teaching efficiency, the animations to easily understand the content, the topic selection, everything was spot on. The programming exercises also helped cement what we learned in the class. The final challenge made us realize how much we actually understood about the concepts and techniques taught in the course.</p><p>It was a fun experience. Now, all this, I expected beforehand, nothing extraordinary. This is all very great of course, but it wasn’t the main thing that blew my mind. What made this a memorable experience and quite unique frankly, was the social aspect and the engagement with the community. From the start of the class, the Udacity team created a Slack workspace for the participants of this challenge and encouraged everyone to participate in group discussions. There was a Facebook group as well, but I mostly used the Slack workspace, and I think so did most of the other students because it was fairly active all the time. It was hard to keep track of all the things and activities going on at a given moment but still, it was manageable.</p><p>A team of TAs and volunteers were always present to solve the queries of the students and help them out if they’re struggling with something, be it a concept taught in the course, a program, an environment error, cutting-edge new research and so on. I mean there were always interesting and informative conversations happening and the vibe of the whole community was very positive.</p><p>They also took several initiatives to further help the community, like Study Buddy, Mentor-ship program, study groups, workshops etc. Many study groups were made, based on the interests of the students, or their geographical location etc. Every weekend, the members of the study group would meet, either locally or through hangout, if they’re far apart, and discuss what they learned, ask questions, help-out each other. They would later on post their group selfies in the Facebook group which also motivated others to do so. You know how people are these days ;)</p><p>A number of extra workshops were held as well, both by Udacity professionals as well as the student participants of the program. They would cover a wide range of topics. Some would explain the concepts taught in the course that the students were having a hard time understanding. Some would show how to debug or troubleshoot a certain kind of problem that the students are having. Some would explain other interesting topics, not covered in the course. Everybody was willing to help out each other and in the process, learn and grow, together as a community.</p><p>This social engagement aspect made a very positive impact on me. This will definitely be one of the most memorable and rewarding experiences of my life, given the toxicity of most of the online communities.</p><p>I have good news as well, great news in fact. I got accepted into the Phase 2 program. I will be able to complete the Deep Learning Nanodegree program, which I was very very eager to do, but couldn’t afford. I am planning to blog about my experience with the Nanodegree as well as the content that I learn there. So, look out for some amazing tutorials and blog posts on Deep Learning and stay tuned. Wish me luck :)</p><p><em>This story first appeared on </em><a href="https://aadimator.com/pytorch-scholarship-challenge-from-facebook/"><em>https://aadimator.com/pytorch-scholarship-challenge-from-facebook/</em></a></p><img src="https://medium.com/_/stat?event=post.clientViewed&referrerSource=full_rss&postId=a9d41733b4b4" width="1" height="1" alt=""><hr><p><a href="https://medium.com/lmdl/pytorch-scholarship-challenge-from-facebook-a9d41733b4b4">PyTorch Scholarship Challenge from Facebook</a> was originally published in <a href="https://medium.com/lmdl">LMDL</a> on Medium, where people are continuing the conversation by highlighting and responding to this story.</p>]]></content:encoded>
        </item>
        <item>
            <title><![CDATA[Learning Machine Learning]]></title>
            <link>https://medium.com/lmdl/learning-machine-learning-e344132f7dfe?source=rss----d1d153c494af---4</link>
            <guid isPermaLink="false">https://medium.com/p/e344132f7dfe</guid>
            <category><![CDATA[machine-learning]]></category>
            <category><![CDATA[coursera]]></category>
            <category><![CDATA[course]]></category>
            <category><![CDATA[mooc]]></category>
            <category><![CDATA[deep-learning]]></category>
            <dc:creator><![CDATA[Aadam]]></dc:creator>
            <pubDate>Sat, 12 Aug 2017 16:47:14 GMT</pubDate>
            <atom:updated>2017-08-12T16:47:26.490Z</atom:updated>
            <content:encoded><![CDATA[<figure><img alt="" src="https://cdn-images-1.medium.com/max/1024/1*YKkbE3b2JgMDHCMwj5oCwA.jpeg" /></figure><p>A while back, I started the Deep Learning course provided by <a href="http://course.fast.ai/">fast.ai</a> and after going through the first few lessons, I felt like I needed to brush up on my Machine Learning skills first if I want to get a deeper understanding of the Deep Learning. It wasn’t that they were going at an extra pace or were covering hard mathematical problems and complex algorithms, but they did require us to learn some material on our own, by reading articles or watching some videos or simulations etc.</p><p>Anyways, I decided to put the fast.ai course on hold for a while and complete a few courses on Machine Learning first. It’s not that I didn’t have any Machine Learning experience before taking that course.</p><figure><img alt="" src="https://cdn-images-1.medium.com/max/1024/1*jNcBw8VT1gv6gx8-zUz_fw.png" /><figcaption>Machine Learning Engineer Nanodegree — Aadam</figcaption></figure><p>I’ve completed the <a href="https://www.udacity.com/course/machine-learning-engineer-nanodegree--nd009">Machine Learning Nanodegree</a> offered by <a href="https://www.udacity.com/">Udacity</a>. It was an amazing experience as I learned a lot of new things and had some hands-on experience, with the problems we face in machine learning and the libraries, tools and the algorithms that are mostly used to solve those problems, by completing several projects. My <strong>capstone project</strong> was related to a <strong>computer vision</strong> problem, the famous dogs-vs-cats classification problem, and I solved it using <strong>CNN</strong>. So, I had a little bit of experience with Deep Learning as well.</p><p>Nonetheless, I still wanted to explore Machine Learning a bit further and to get more comfortable with it. I had a few courses on my mind that were better suited for my situation and on top was the<strong> </strong><a href="https://www.coursera.org/learn/machine-learning"><strong>Machine Learning</strong></a> course taught by <strong>Andrew Ng</strong>. I had started this course half an year ago, but because of some forgettable reasons, I wasn’t able to complete it.</p><p>This was the perfect course for me as I had some experience with Machine Learning but I didn’t fully understand some of the algorithms and the techniques we used. This course provided just that, a little more detail as to why we do such and such and why and how this works. The teaching style of Andrew Ng was phenomenal, the way he could explain difficult concepts without dumbing them down.</p><p>You can’t imagine my surprise when I found out today that Andrew Ng released 5 new courses on Deep Learning, the <a href="https://www.coursera.org/specializations/deep-learning"><strong>Deep Learning Specialization</strong></a>.</p><figure><a href="https://www.coursera.org/specializations/deep-learning"><img alt="" src="https://cdn-images-1.medium.com/max/742/1*TVHkVwszQK47vUAOHeOjEQ.png" /></a><figcaption>Deep Learning Specialization — Coursera</figcaption></figure><p>Given the quality of the first <a href="https://www.coursera.org/learn/machine-learning">Machine Learning</a> course by Andrew Ng and the positive feedback it got, chances are that this specialization is going to be quite amazing as well.</p><p>This gave me extra motivation to complete the <a href="https://www.coursera.org/learn/machine-learning">Machine Learning</a> course first and then delve into this specialization to whet my appetite. By looking at the first two weeks, I am positive that this is going to be a very rewarding experience for me.</p><img src="https://medium.com/_/stat?event=post.clientViewed&referrerSource=full_rss&postId=e344132f7dfe" width="1" height="1" alt=""><hr><p><a href="https://medium.com/lmdl/learning-machine-learning-e344132f7dfe">Learning Machine Learning</a> was originally published in <a href="https://medium.com/lmdl">LMDL</a> on Medium, where people are continuing the conversation by highlighting and responding to this story.</p>]]></content:encoded>
        </item>
        <item>
            <title><![CDATA[Fast.ai — Initial Thoughts]]></title>
            <link>https://medium.com/lmdl/fast-ai-initial-thoughts-636904c05666?source=rss----d1d153c494af---4</link>
            <guid isPermaLink="false">https://medium.com/p/636904c05666</guid>
            <category><![CDATA[thoughts]]></category>
            <category><![CDATA[deep-learning]]></category>
            <category><![CDATA[machine-learning]]></category>
            <category><![CDATA[course]]></category>
            <category><![CDATA[computer-vision]]></category>
            <dc:creator><![CDATA[Aadam]]></dc:creator>
            <pubDate>Fri, 11 Aug 2017 20:17:41 GMT</pubDate>
            <atom:updated>2017-08-11T20:17:52.466Z</atom:updated>
            <content:encoded><![CDATA[<p>What makes the <a href="http://course.fast.ai/">fast.ai</a> course on deep learning different from many others !</p><figure><img alt="" src="https://cdn-images-1.medium.com/max/1024/1*KBsb9WJ9a_23SXXDDcso5A.jpeg" /><figcaption>fast.ai — Jeremy Howard</figcaption></figure><p>For a long time now, I’ve been planning to start learning about the deep learning, but whenever I start reading about it, either through books such as <a href="https://www.amazon.com/Deep-Learning-Adaptive-Computation-Machine/dp/0262035618">The MIT Press Deep Learning</a> book, or through some online video or MOOCs, I get bombarded with strange mathematical formulas and complex equations. Of course this complex mathematics is quite necessary to understand Deep Learning models but it also repels a beginner from learning about this field, as a beginner is more result oriented.</p><p>If I was a PhD student and I was researching to make a specific algorithm perform better in some way, sure I’d have to learn about all those equations and formulas, but the reality is, I’m not, for now. I am just a curious student, who’d like to get a general overview about how Deep Learning works and build some apps to test different models on the real world data.</p><p>But for a long time, most of the resources available to learn about Deep Learning were focusing on those PhD level students, quite boring and technical, with little to no practical projects whatsoever. So, whenever I tried starting this endeavor to learn about Deep Learning, just after a day or two, I’d get frustrated and abandon it altogether.</p><p>You can’t imagine my surprise when I learned about this course, <a href="http://course.fast.ai/">fast.ai</a>, taught by <strong>Jeremy Howard</strong>. The approach that they are using to teach Deep Learning is quite opposite to what’s being used elsewhere. Instead of diving deeper into the technicalities from the start, they are using a top-down code-first approach where they let the student experiment with different algorithms and techniques by implementing them to solve real world problems, like from Kaggle competitions etc, from the first lecture.</p><p>This is what I’ve been looking for all along. A way to ease into the Deep Learning field, experiment with different models, and when I get comfortable then delve deeper into the mathematics.</p><p>The main objective or the teaching strategy being followed in this course seems quite interesting and attractive but let’s see how well it’s executed.</p><p>I’m hopeful that this is going to be an amazing experience for me, I’ll learn a lot and practice a lot.</p><p>I’ll keep blogging about my experience taking this course, the things I liked, the things I didn’t, the problems I faced and solutions to those. Let’s see how it turns out.</p><img src="https://medium.com/_/stat?event=post.clientViewed&referrerSource=full_rss&postId=636904c05666" width="1" height="1" alt=""><hr><p><a href="https://medium.com/lmdl/fast-ai-initial-thoughts-636904c05666">Fast.ai — Initial Thoughts</a> was originally published in <a href="https://medium.com/lmdl">LMDL</a> on Medium, where people are continuing the conversation by highlighting and responding to this story.</p>]]></content:encoded>
        </item>
    </channel>
</rss>