<?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[Sigmoid - Medium]]></title>
        <description><![CDATA[Making Machine Learning more accessible. One line of code at a time. - Medium]]></description>
        <link>https://medium.com/sigmoid?source=rss----7ece317bbaef---4</link>
        <image>
            <url>https://cdn-images-1.medium.com/proxy/1*TGH72Nnw24QL3iV9IOm4VA.png</url>
            <title>Sigmoid - Medium</title>
            <link>https://medium.com/sigmoid?source=rss----7ece317bbaef---4</link>
        </image>
        <generator>Medium</generator>
        <lastBuildDate>Mon, 16 Nov 2026 19:11:00 GMT</lastBuildDate>
        <atom:link href="https://medium.com/feed/sigmoid" rel="self" type="application/rss+xml"/>
        <webMaster><![CDATA[yourfriends@medium.com]]></webMaster>
        <atom:link href="http://medium.superfeedr.com/" rel="hub"/>
        <item>
            <title><![CDATA[A Brief Introduction To GANs (and how to code them)]]></title>
            <description><![CDATA[<div class="medium-feed-item"><p class="medium-feed-image"><a href="https://medium.com/sigmoid/a-brief-introduction-to-gans-and-how-to-code-them-2620ee465c30?source=rss----7ece317bbaef---4"><img src="https://cdn-images-1.medium.com/max/2328/1*RyX2xNxTZCKMUW_lErbJVw.png" width="2328"></a></p><p class="medium-feed-snippet">With explanations of the math and code</p><p class="medium-feed-link"><a href="https://medium.com/sigmoid/a-brief-introduction-to-gans-and-how-to-code-them-2620ee465c30?source=rss----7ece317bbaef---4">Continue reading on Sigmoid »</a></p></div>]]></description>
            <link>https://medium.com/sigmoid/a-brief-introduction-to-gans-and-how-to-code-them-2620ee465c30?source=rss----7ece317bbaef---4</link>
            <guid isPermaLink="false">https://medium.com/p/2620ee465c30</guid>
            <category><![CDATA[data-science]]></category>
            <category><![CDATA[tutorial]]></category>
            <category><![CDATA[programming]]></category>
            <category><![CDATA[machine-learning]]></category>
            <category><![CDATA[artificial-intelligence]]></category>
            <dc:creator><![CDATA[Sarvasv Kulpati]]></dc:creator>
            <pubDate>Mon, 22 Apr 2019 06:42:34 GMT</pubDate>
            <atom:updated>2019-05-04T04:20:07.744Z</atom:updated>
        </item>
        <item>
            <title><![CDATA[A Brief Introduction to Markov Chains]]></title>
            <link>https://medium.com/sigmoid/rl-markov-chains-dbf2f37e8b69?source=rss----7ece317bbaef---4</link>
            <guid isPermaLink="false">https://medium.com/p/dbf2f37e8b69</guid>
            <category><![CDATA[deep-learning]]></category>
            <category><![CDATA[machine-learning]]></category>
            <category><![CDATA[reinforcement-learning]]></category>
            <category><![CDATA[markov-chains]]></category>
            <category><![CDATA[artificial-intelligence]]></category>
            <dc:creator><![CDATA[Rishabh Anand]]></dc:creator>
            <pubDate>Wed, 27 Feb 2019 11:03:11 GMT</pubDate>
            <atom:updated>2019-02-27T11:03:11.351Z</atom:updated>
            <content:encoded><![CDATA[<h4>A general guide on what makes the Markov Decision Process tick</h4><p><strong><em>tldr;</em></strong><em> This is part of a series of reference articles teaching the concepts that drive Reinforcement Learning. We’ll be starting off simple, incrementally moving on to more complex concepts further down the road.</em></p><p>A Markov Chain is a stochastic (always changing) model that is used to predict/estimate/guess the outcome of an event given only the previous state and its action. The state refers to the current ‘slice’ of the environment. It’s the particular condition that an agent is contained in at a specific time step.</p><p>For example, in Sonic the Hedgehog, a state refers to the current pixel intensity values that represent the game screen.</p><figure><img alt="" src="https://cdn-images-1.medium.com/max/477/1*GnFKk6JZqv3Uv51u_9BaSg.png" /><figcaption>The state refers to the current pixel values that make up this particular game screen at time 0:05 seconds</figcaption></figure><p>It can be represented by a matrix of values pertaining to the pixel values. When used in a Reinforcement Learning algorithm, it can be represented as something like this:</p><figure><img alt="" src="https://cdn-images-1.medium.com/max/477/1*0yHoBrTMH1neWFwpu-EshA.png" /><figcaption>The different color RGB channels that form the current state</figcaption></figure><iframe src="https://cdn.embedly.com/widgets/media.html?src=https%3A%2F%2Fupscri.be%2F5008b6-2%3Fas_embed%3Dtrue&amp;dntp=1&amp;url=https%3A%2F%2Fupscri.be%2F5008b6-2%2F&amp;key=a19fcc184b9711e1b4764040d3dc5c07&amp;type=text%2Fhtml&amp;schema=upscri" width="800" height="400" frameborder="0" scrolling="no"><a href="https://medium.com/media/c12b608fccfefbccf9e6f493ef5cb71f/href">https://medium.com/media/c12b608fccfefbccf9e6f493ef5cb71f/href</a></iframe><h4>The Markov Chain</h4><p>The Markov Chain is a model used to describe a sequence of consecutive events where the probability or chance of an event depends only on the event before it.</p><p>If a sequence of events exhibits the Markov Property of the reliance on the previous state, then the sequence is called ‘Markovian’ in nature.</p><figure><img alt="" src="https://cdn-images-1.medium.com/max/477/1*bnAjR8ulmRmdMiPZTcSt0Q.png" /><figcaption>An example of a Markov Chain with numbers for visualization purposes</figcaption></figure><p>The figure above shows two states, A and E. The probability of an event occurring depends on the current state. A movement from A to E or vice versa depends on whether the ‘character’ was previously on A or E.</p><p>If the previous state or location was A, then the probability of going to E is 0.4 while the probability of staying on A is 0.6 (fundamentally A to A).</p><p>The probability of going from E to A is 0.7 while the probability of staying on E is 0.3 (E to E).</p><p>Hopefully, this can help you visualize the process of moving from state to state depending on the current state. If we were to write this mathematically, it is simply the probability of an event happening in the future time step, <strong>S<em>t+1</em></strong>, <strong><em>s’</em></strong>, given the current state <strong>S<em>t</em></strong>, <strong><em>s</em></strong>:</p><figure><img alt="" src="https://cdn-images-1.medium.com/proxy/1*MttGDZm6XvBMDbJsrDzSIA.png" /></figure><h4>The advent of Markov Chains</h4><p>For some problems in Reinforcement Learning, the actions performed in a particular state is directly related to the previous state, the actions performed in that state and the rewards that the agent receives upon performing said actions.</p><p>This Markovian property of a problem greatly benefits us as it makes the agent really versatile while being really lightweight compared to deep neural networks with heavy parameters.</p><p>Furthermore, Markov Chains are used in a process called Markov Reward Process where the agent (whose objective is to maximize the rewards earned in the task) in the current task is rewarded based on its performance in the current time step.</p><h3>In a nutshell</h3><p>Markov Chains are really useful in Reinforcement Learning as it has enabled us to achieve and even exceed human performance in many areas and problems from teaching robots how to handle objects with care to beating difficult Atari games that were previously never beaten by statistical Machine Learning.</p><p>Over the next few articles, we’ll go through the various forms and applications of the Markov Property and how useful it is when dealing with certain problems.</p><p>For the next article, I am planning to write a small dictionary of all the terminology used in the field of Reinforcement Learning as a reference piece. If you have any suggestions for RL articles or questions in general, feel free to drop in a comment below.</p><p>With that, I’ll see you in the next one.</p><p>Original article by <a href="https://medium.com/u/50c04ecf0ec5">Rishabh Anand</a></p><h4>Related articles</h4><p>Check out my other articles on technology and Machine Learning, and reviews of up-and-coming software innovations.</p><ul><li><a href="https://medium.com/sigmoid/https-medium-com-rishabh-anand-on-the-origin-of-genetic-algorithms-fc927d2e11e0">A Comprehensive Guide to Genetic Algorithms (and how to code them)</a></li><li><a href="https://hackernoon.com/introducing-tensorflow-js-3f31d70f5904">Introducing TensorFlow.js 🎉</a></li><li><a href="https://hackernoon.com/catgan-cat-face-generation-using-gans-f44663586d6b">CatGAN: cat face generation using GANs</a></li><li><a href="https://towardsdatascience.com/tensorflow-or-tensorno-c9c6c6c2f992">TensorFlow or TensorNo?</a></li></ul><iframe src="https://cdn.embedly.com/widgets/media.html?src=https%3A%2F%2Fupscri.be%2F5008b6-2%3Fas_embed%3Dtrue&amp;dntp=1&amp;url=https%3A%2F%2Fupscri.be%2F5008b6-2%2F&amp;key=a19fcc184b9711e1b4764040d3dc5c07&amp;type=text%2Fhtml&amp;schema=upscri" width="800" height="400" frameborder="0" scrolling="no"><a href="https://medium.com/media/c12b608fccfefbccf9e6f493ef5cb71f/href">https://medium.com/media/c12b608fccfefbccf9e6f493ef5cb71f/href</a></iframe><img src="https://medium.com/_/stat?event=post.clientViewed&referrerSource=full_rss&postId=dbf2f37e8b69" width="1" height="1" alt=""><hr><p><a href="https://medium.com/sigmoid/rl-markov-chains-dbf2f37e8b69">A Brief Introduction to Markov Chains</a> was originally published in <a href="https://medium.com/sigmoid">Sigmoid</a> on Medium, where people are continuing the conversation by highlighting and responding to this story.</p>]]></content:encoded>
        </item>
        <item>
            <title><![CDATA[Hi there from Sigmoid . We need your help.]]></title>
            <link>https://medium.com/sigmoid/hi-there-from-sigmoid-we-need-your-help-b34f8a0652ca?source=rss----7ece317bbaef---4</link>
            <guid isPermaLink="false">https://medium.com/p/b34f8a0652ca</guid>
            <dc:creator><![CDATA[Sarvasv Kulpati]]></dc:creator>
            <pubDate>Sun, 24 Feb 2019 08:10:33 GMT</pubDate>
            <atom:updated>2019-02-24T08:10:32.934Z</atom:updated>
            <content:encoded><![CDATA[<p>Hello everyone!</p><p><em>Check out our </em><a href="https://upscri.be/b69b1a/"><strong><em>newsletter for learning machine learning, 5 minutes at a time</em></strong></a></p><p>Welcome to our publication. <a href="https://medium.com/u/50c04ecf0ec5">Rishabh Anand</a> and I, <a href="https://medium.com/u/2d5aff86a200">Sarvasv Kulpati</a> decided to start this publication to share our knowledge about AI in the most simple way possible.</p><p>We’re tired of blog posts with a ton of jargon, complex, unexplained math, and cryptic implementations in code. Hopefully, we’ll be different with Sigmoid.</p><p>So we want your input. <strong>What would you like to see us write?</strong> What are you the most interested about in AI? What are you the most confused about? If there’s anything at all, please do ping us. We’re writing this for you, and so, it’s only fair that we take into account your input.</p><p>If you’re interested, we’re also running a mini newsletter 3 times a week that explains<strong> machine learning concepts in 5 minutes</strong>. <a href="https://upscri.be/b69b1a/"><strong>You can sign up for that here</strong></a></p><img src="https://medium.com/_/stat?event=post.clientViewed&referrerSource=full_rss&postId=b34f8a0652ca" width="1" height="1" alt=""><hr><p><a href="https://medium.com/sigmoid/hi-there-from-sigmoid-we-need-your-help-b34f8a0652ca">Hi there from Sigmoid 👋. We need your help.</a> was originally published in <a href="https://medium.com/sigmoid">Sigmoid</a> on Medium, where people are continuing the conversation by highlighting and responding to this story.</p>]]></content:encoded>
        </item>
        <item>
            <title><![CDATA[Linear Regression From Scratch With Python]]></title>
            <link>https://medium.com/sigmoid/linear-regression-from-scratch-with-python-5c33712a1cec?source=rss----7ece317bbaef---4</link>
            <guid isPermaLink="false">https://medium.com/p/5c33712a1cec</guid>
            <category><![CDATA[machine-learning]]></category>
            <category><![CDATA[artificial-intelligence]]></category>
            <category><![CDATA[python]]></category>
            <category><![CDATA[ai]]></category>
            <dc:creator><![CDATA[Sarvasv Kulpati]]></dc:creator>
            <pubDate>Sat, 02 Feb 2019 02:09:49 GMT</pubDate>
            <atom:updated>2019-02-02T02:09:49.095Z</atom:updated>
            <content:encoded><![CDATA[<h4>Implementing one of the most basic concepts in Data Science</h4><figure><img alt="" src="https://cdn-images-1.medium.com/max/1024/1*0WDn5lxEY2qF2Ue3LdxnTw.png" /></figure><p>As one of the most basic concepts in Data Science, I thought that it would be a good idea to cover the fundamentals of how linear regression works.</p><p>Here’s a link to the Github Repo:</p><p><a href="https://github.com/sarvasvkulpati/LinearRegression">sarvasvkulpati/LinearRegression</a></p><h3>What Is Linear Regression?</h3><p>Linear regression is a method for approximating a linear relationship between two variables. While that may sound complicated, all it really means is that it takes some input variable, like the age of a house, and finds out how it’s related to another variable, for example, the price it sells at.</p><figure><img alt="" src="https://cdn-images-1.medium.com/max/1000/1*gTFluWEsDhe8Qku-LG2O8w.jpeg" /><figcaption>Example of data with a linear relationship</figcaption></figure><blockquote>Linear regression takes some input variable, like the age of a house, and finds out how it’s related to another variable, for example, the price it sells at.</blockquote><p>We use it when the data has a <strong>linear relationship</strong>, which means that when you plot the points on a graph, the data lies approximately in the shape of a straight line.</p><p>The goal of linear regression is to find a line that best fits a set of data points.</p><blockquote>In terms of general intuition, linear regression guesses a line that fits the data, sees how incorrect it was, and then adjusts itself to become slightly more accurate. It repeats this process until it’s reduced the error as much as possible.</blockquote><p>Linear Regression involves a couple of steps:</p><ol><li>Randomly initializing parameters for the hypothesis function</li><li>Computing the mean squared error</li><li>Calculating the partial derivatives</li><li>Updating the parameters based on the derivatives and the learning rate</li><li>Repeating from 2–4 until the error is minimized</li></ol><p>While these may sound complicated, let’s go through them step by step and understand what each of them means.</p><iframe src="https://cdn.embedly.com/widgets/media.html?src=https%3A%2F%2Fupscri.be%2F50f6f7%3Fas_embed%3Dtrue&amp;dntp=1&amp;url=https%3A%2F%2Fupscri.be%2F50f6f7%2F&amp;key=a19fcc184b9711e1b4764040d3dc5c07&amp;type=text%2Fhtml&amp;schema=upscri" width="800" height="400" frameborder="0" scrolling="no"><a href="https://medium.com/media/bcfcba849b7194a30b5504ef2cc161d1/href">https://medium.com/media/bcfcba849b7194a30b5504ef2cc161d1/href</a></iframe><h3>The Data</h3><p>For linear regression, we need a dataset that follows a linear pattern to train our model on.</p><p>The python package sklearn comes with an inbuilt function to create a linear dataset:</p><iframe src="" width="0" height="0" frameborder="0" scrolling="no"><a href="https://medium.com/media/e3a8f10495770014d14e15f229c66952/href">https://medium.com/media/e3a8f10495770014d14e15f229c66952/href</a></iframe><h3>The Hypothesis Function</h3><p>The <strong>linear equation</strong> is the standard form that represents a straight line on a graph, where m represents the <strong>gradient- how steep the line is</strong>, and b represents the <strong>y-intercept- where the line crosses the y-axis</strong>.</p><p>You might remember this as one of the first equations you learned in school.</p><figure><img alt="" src="https://cdn-images-1.medium.com/max/534/1*TEzHQl-H0E4YKOpInAN_ZQ.png" /></figure><p>The Hypothesis Function is the exact same function in the notation of Linear Regression.</p><figure><img alt="" src="https://cdn-images-1.medium.com/max/686/1*oNsv50WV-2gGXqpAT6Snag.png" /></figure><p>The two variables we can change — m and b — are represented as parameters θ₁ and θ₀.</p><p>We’ll represent the function in python like so:</p><iframe src="" width="0" height="0" frameborder="0" scrolling="no"><a href="https://medium.com/media/d3c7fbfc6ba905c0a35a3bf69a3d06a9/href">https://medium.com/media/d3c7fbfc6ba905c0a35a3bf69a3d06a9/href</a></iframe><p>In the beginning, we <strong>randomly initialize our parameters</strong>, which means we give θ₁ and θ₀ random values to begin with. This will output a random line, maybe something like this:</p><figure><img alt="" src="https://cdn-images-1.medium.com/max/500/1*UQccWe9TIz__XXw_28gCcw.jpeg" /></figure><p>We can create a function in python that displays the graph with the line using the matplotlib and numpy libraries:</p><iframe src="" width="0" height="0" frameborder="0" scrolling="no"><a href="https://medium.com/media/f3c335595b9dcb5c9a2e3a66b38ecd80/href">https://medium.com/media/f3c335595b9dcb5c9a2e3a66b38ecd80/href</a></iframe><p>Then, we can display a line with randomly initialized θ₁ and θ₀ values</p><iframe src="" width="0" height="0" frameborder="0" scrolling="no"><a href="https://medium.com/media/c02ea988e42cf8fe7f8e923560274d87/href">https://medium.com/media/c02ea988e42cf8fe7f8e923560274d87/href</a></iframe><p>When we run that function, it’ll output a random line, maybe something like this:</p><figure><img alt="" src="https://cdn-images-1.medium.com/max/1024/1*soyrYetGiQX2fE0nIlYRGQ.png" /></figure><h3>The Error Function</h3><p>Clearly, the line drawn in the graph above is wrong. But how wrong is it? That’s what the <strong>error function</strong> is for — <strong>it calculates the total error of your line</strong>. We’ll be using an error function called the Mean Squared Error function, or MSE, represented by the letter J.</p><figure><img alt="" src="https://cdn-images-1.medium.com/max/1024/1*94Gc_tf4a5WPxxugOI5uWw.png" /></figure><p>Now while that may look complicated, what it’s doing is actually quite simple.</p><ol><li>To find out how “wrong” the line is, we need to find out how far it is from each point. To do this, we subtract the actual value yᵢ from the predicted value h(xᵢ).</li><li>However, we don’t want the error to be negative, so to make sure it’s positive at all times, we square this value.</li><li>M is the number of points in our dataset. We then repeat this subtraction and squaring for all m points</li><li>Finally, we divide the error by 2. This will help us later when we are updating our parameters.</li></ol><p>Here’s what that looks like in code:</p><iframe src="" width="0" height="0" frameborder="0" scrolling="no"><a href="https://medium.com/media/1838a1db47a99c97c11c0daff3ac8faa/href">https://medium.com/media/1838a1db47a99c97c11c0daff3ac8faa/href</a></iframe><p>Now that we have a value for how wrong our function is, we need to adjust the function to reduce this error.</p><h3>Calculating Derivatives</h3><p>Our goal with linear regression was to find the line which best fits a set of data points. In other words, it’s the line that’s the least incorrect or has the lowest error.</p><p>If we graph our parameters against the error (i.e graphing the cost function), we’ll find that it forms something similar to the graph below. At the lowest point of that graph, the error is at it’s lowest. Finding this point is called <strong>minimizing the cost function</strong>.</p><figure><img alt="" src="https://cdn-images-1.medium.com/max/1024/1*91DQMNKmNIdncqx6FsB4Iw.png" /></figure><p>To do this, we need to consider what happens at the bottom of the graph — the gradient is zero. So <strong>to minimize the cost function, we need to get the gradient to zero.</strong></p><p>The gradient is given by the derivative of the function, and the partial derivatives of the functions are:</p><figure><img alt="" src="https://cdn-images-1.medium.com/max/938/1*8lUp6KgvPw2GTDy96s0TNQ.png" /></figure><p>We can calculate the derivatives using the following function</p><iframe src="" width="0" height="0" frameborder="0" scrolling="no"><a href="https://medium.com/media/ace0e5665aac4802acb312dfbbce794e/href">https://medium.com/media/ace0e5665aac4802acb312dfbbce794e/href</a></iframe><h3>Updating The Parameters Based On The Learning Rate</h3><p>Now we need to update our parameters to reduce the gradient. To do this, we use the gradient update rule</p><p><strong>Alpha (α) is what we call the Learning rate, which is a small number that allows the parameters to be updated by a small amount</strong>. As mentioned above, we are trying to update the gradient such that it’s closer to zero (the bottom). The learning rate helps guide the network to the lowest point on the curve by small amounts.</p><figure><img alt="" src="https://cdn-images-1.medium.com/max/668/1*VOqzyi2rcQLxL6hTp5Y1PA.png" /></figure><iframe src="" width="0" height="0" frameborder="0" scrolling="no"><a href="https://medium.com/media/991edbb5f7f68beff34f09290e26561d/href">https://medium.com/media/991edbb5f7f68beff34f09290e26561d/href</a></iframe><h3>Minimizing the Cost Function</h3><p>Now we repeat these steps — checking the error, calculating the derivatives, and updating the weights until the error is as low as possible. This is called minimizing the cost function.</p><p>We can now tie all our code together in a function in python:</p><iframe src="" width="0" height="0" frameborder="0" scrolling="no"><a href="https://medium.com/media/ae98c3e5f45ed36ff99ca1c948fb59de/href">https://medium.com/media/ae98c3e5f45ed36ff99ca1c948fb59de/href</a></iframe><p>When you run this, it randomly initializes θ₁ and θ₀, and then iterates 1000 times to update the parameters to reduce the error. Every 100 times, it outputs what the line looks like to show us our progress.</p><p>Once your error is minimized, your line should now be the best possible fit to approximate the data!</p><figure><img alt="" src="https://cdn-images-1.medium.com/max/480/1*O5xIOeMQNtxoFcPBIQ-Aog.gif" /></figure><h3>Conclusion</h3><p>Here are some key terms we learned —</p><p><strong>Simple linear regression — </strong>Finds the relationship between two variables that are linearly correlated. E.g. finding the relationship between the size of a house and the price of a house</p><p><strong>Linear relationship — </strong>When you plot the dataset on a graph, the data lies approximately in the shape of a straight line.</p><p><strong>Linear equation — </strong>y = mx +b. The standard form that represents a straight line on a graph, where m represents the <strong>gradient</strong>, and b represents the <strong>y-intercept.</strong></p><p><strong>Gradient —</strong> How steep the line is</p><p><strong>Y-intercept — </strong>Where<strong> </strong>the line crosses the y-axis</p><p><strong>Random Initialization — </strong>Giving parameters random values to begin with</p><p><strong>Cost function —</strong> Calculates the total error of your line</p><p><strong>Minimizing the cost function — </strong>Reducing the value of the cost function until the error is minimized.</p><p><strong>Learning rate (alpha (α)) — </strong>A small number that allows the parameters to be updated by a tiny amount.</p><p>After reading this article, I hope you now have a better understanding of linear regression and the gradient update rule, which is foundational for other concepts in the field.</p><p><strong>Thanks for reading,</strong></p><p><strong>Sarvasv</strong></p><p><strong>Want to chat? Find me on </strong><a href="https://twitter.com/SarvasvKulpati"><strong>Twitter</strong></a><strong> and </strong><a href="https://www.linkedin.com/in/sarvasvkulpati/"><strong>Linkedin</strong></a></p><p><strong>Here’s some other posts I’ve written</strong></p><ul><li><a href="https://hackernoon.com/you-need-to-go-on-an-information-diet-def2f5a3fd5b">You Need To Go On An Information Diet</a></li><li><a href="https://medium.freecodecamp.org/what-i-learned-from-creating-and-shipping-my-first-app-in-a-day-9f79010765f0">What I learned from creating and shipping my first app in a day</a></li></ul><img src="https://medium.com/_/stat?event=post.clientViewed&referrerSource=full_rss&postId=5c33712a1cec" width="1" height="1" alt=""><hr><p><a href="https://medium.com/sigmoid/linear-regression-from-scratch-with-python-5c33712a1cec">Linear Regression From Scratch With Python</a> was originally published in <a href="https://medium.com/sigmoid">Sigmoid</a> on Medium, where people are continuing the conversation by highlighting and responding to this story.</p>]]></content:encoded>
        </item>
        <item>
            <title><![CDATA[A Comprehensive Guide to Genetic Algorithms (and how to code them)]]></title>
            <description><![CDATA[<div class="medium-feed-item"><p class="medium-feed-image"><a href="https://medium.com/sigmoid/https-medium-com-rishabh-anand-on-the-origin-of-genetic-algorithms-fc927d2e11e0?source=rss----7ece317bbaef---4"><img src="https://cdn-images-1.medium.com/max/900/1*Bylye2rZ5HHI0xcz9qeZUA.jpeg" width="900"></a></p><p class="medium-feed-snippet">On the Origin of Genetic Algorithms</p><p class="medium-feed-link"><a href="https://medium.com/sigmoid/https-medium-com-rishabh-anand-on-the-origin-of-genetic-algorithms-fc927d2e11e0?source=rss----7ece317bbaef---4">Continue reading on Sigmoid »</a></p></div>]]></description>
            <link>https://medium.com/sigmoid/https-medium-com-rishabh-anand-on-the-origin-of-genetic-algorithms-fc927d2e11e0?source=rss----7ece317bbaef---4</link>
            <guid isPermaLink="false">https://medium.com/p/fc927d2e11e0</guid>
            <category><![CDATA[machine-learning]]></category>
            <category><![CDATA[genetic-algorithm]]></category>
            <category><![CDATA[natural-selection]]></category>
            <category><![CDATA[reinforcement-learning]]></category>
            <category><![CDATA[evolution]]></category>
            <dc:creator><![CDATA[Rishabh Anand]]></dc:creator>
            <pubDate>Tue, 28 Aug 2018 01:19:17 GMT</pubDate>
            <atom:updated>2018-08-28T01:19:41.489Z</atom:updated>
        </item>
    </channel>
</rss>