<?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[Stories by Durand D&#39;souza on Medium]]></title>
        <description><![CDATA[Stories by Durand D&#39;souza on Medium]]></description>
        <link>https://medium.com/@dldx?source=rss-ede5d822a083------2</link>
        <image>
            <url>https://cdn-images-1.medium.com/fit/c/150/150/0*mKV6CqQm0JKlhEJe.</url>
            <title>Stories by Durand D&amp;#39;souza on Medium</title>
            <link>https://medium.com/@dldx?source=rss-ede5d822a083------2</link>
        </image>
        <generator>Medium</generator>
        <lastBuildDate>Thu, 19 Nov 2026 08:32:46 GMT</lastBuildDate>
        <atom:link href="https://medium.com/@dldx/feed" rel="self" type="application/rss+xml"/>
        <webMaster><![CDATA[yourfriends@medium.com]]></webMaster>
        <atom:link href="http://medium.superfeedr.com/" rel="hub"/>
        <item>
            <title><![CDATA[Letter to my MP: Let’s have a Carbon Fee and Dividend policy in the UK!]]></title>
            <link>https://medium.com/@dldx/letter-to-my-mp-lets-have-a-carbon-fee-and-dividend-policy-in-the-uk-c83305390843?source=rss-ede5d822a083------2</link>
            <guid isPermaLink="false">https://medium.com/p/c83305390843</guid>
            <category><![CDATA[environment]]></category>
            <category><![CDATA[carbon-tax]]></category>
            <category><![CDATA[climate-change]]></category>
            <category><![CDATA[uk-politics]]></category>
            <dc:creator><![CDATA[Durand D'souza]]></dc:creator>
            <pubDate>Fri, 06 Oct 2017 09:30:09 GMT</pubDate>
            <atom:updated>2017-10-06T09:30:09.130Z</atom:updated>
            <cc:license>https://creativecommons.org/licenses/by-sa/4.0/</cc:license>
            <content:encoded><![CDATA[<figure><img alt="" src="https://cdn-images-1.medium.com/max/1024/1*DhOBOKzGMsENyErRWBX6Ug.jpeg" /><figcaption>Credit: John Englart (Takver). CC by SA 2.0</figcaption></figure><blockquote>Dear Anna Soubry,</blockquote><blockquote>I am writing to you because of my deep concerns about the climate crisis and because I believe that you, as a moderate, business- and innovation-friendly MP, are well poised to advocate for a carbon fee and dividend policy. As an MP who has visited refugee camps, I’m sure you are well aware of the fact that the climate crisis will displace millions of the most vulnerable people in the world.</blockquote><blockquote>As you may know, under the Climate Change Act, the UK has legally binding emission reduction targets and we are currently on track to meet our 2018–2022 targets due to the steep decline in coal use over the past couple of years. This decline is mainly due to the increase in the carbon price floor that the Conservative government legislated in 2015 and has been hugely effective in reducing our emissions. This market-friendly policy has enabled a transition away from coal.</blockquote><blockquote>Unfortunately, the relatively low carbon price floor coupled with cheaper natural gas prices has led to an increase in natural gas burning. This is not sustainable, especially if the UK sources more natural gas from fracking, a process which releases huge amounts of methane (a greenhouse gas 100x as potent as CO2 over a 10 year period and 36x as potent as CO2 over a 100 year period) into the atmosphere and by many accounts is almost as bad as burning coal. As a result of these forecasts, the UK is not on track to meet its 2023–2027 reduction targets. According to the Committee on Climate Change, current plans will only deliver half of the required emissions by 2030.</blockquote><blockquote>But there is a clear, business-friendly solution that could make a huge difference. A carbon fee and dividend — a policy that puts a steadily rising fee on fossil fuels at source (eg. at the oil well, gas extraction site and port of entry) and returns all of the proceeds directly back to all citizens in equal measures — could empower British companies to plan long-term and develop innovative new solutions. With a carbon fee incentive structure, the UK could lead the world in mass electric car ownership, smart grid technology, and new forms of renewable energy such as tidal, wave and offshore wind, which we are already pioneers of. The head start that UK businesses receive will allow us to sell our expertise to the rest of the world. All this potential for growth is only possible however if the UK government puts a price on carbon.</blockquote><blockquote>Many countries around the world are adopting such a measure, notably Canada, where B.C. was a pioneer of the revenue-neutral carbon tax back in 2008. In B.C., emissions have fallen despite a growing population and the economy has grown significantly. In the UK, a steadily rising carbon tax could lead to far fewer deaths from air pollution, which already costs the country greatly, as well as setting an example to the rest of the world.</blockquote><blockquote>I believe the new Climate Minister, Claire Perry, is already acquainted with this proposal. Please let her know that we in Broxtowe also support urgent action on climate change and ask her what it would take to be able to introduce this policy as a bill in Parliament.</blockquote><blockquote>Thank you very much for your time. I look forward to hearing back from you.</blockquote><blockquote>Yours sincerely,<br>Durand D’souza</blockquote><img src="https://medium.com/_/stat?event=post.clientViewed&referrerSource=full_rss&postId=c83305390843" width="1" height="1" alt="">]]></content:encoded>
        </item>
        <item>
            <title><![CDATA[The perils of big data for our democracy.]]></title>
            <link>https://medium.com/@dldx/the-perils-of-big-data-for-our-democracy-6ddf3d12cb06?source=rss-ede5d822a083------2</link>
            <guid isPermaLink="false">https://medium.com/p/6ddf3d12cb06</guid>
            <category><![CDATA[uk-politics]]></category>
            <category><![CDATA[brexit]]></category>
            <category><![CDATA[politics]]></category>
            <category><![CDATA[big-data]]></category>
            <category><![CDATA[democracy]]></category>
            <dc:creator><![CDATA[Durand D'souza]]></dc:creator>
            <pubDate>Tue, 09 May 2017 07:06:28 GMT</pubDate>
            <atom:updated>2017-10-06T09:38:55.501Z</atom:updated>
            <cc:license>http://creativecommons.org/licenses/by/4.0/</cc:license>
            <content:encoded><![CDATA[<figure><img alt="" src="https://cdn-images-1.medium.com/max/1024/1*P2l3My3KPni0GZPzBwYK2w.png" /></figure><p>I just read <a href="https://www.theguardian.com/technology/2017/may/07/the-great-british-brexit-robbery-hijacked-democracy">this new article</a> by Guardian journalist Carole Cadwalladr and it is possibly the most terrifying one I’ve read in a long while… terrifying enough for me to pen my thoughts here… It’s a long article for sure but well-worth reading so I suggest you go ahead and do that now before continuing with the rest of my piece! If you don’t have the time, here’s my short summary:</p><p>A number of data science “psych-ops” companies owned by billionaires Robert Mercer and Peter Thiel have bought huge data sets filled with offline information about you (such as your magazine subscriptions or airline trips you’ve taken) and cross-correlated them with Facebook (and possibly Google?) tracking analytics about you (the pages you liked, the websites you’ve visited and the emotions you’ve attributed to particular posts) to figure out your political and psychological profile. They’ve then used this information to target specific voters (eg. angry fishermen pissed off about EU rules or workers at a company which just went bankrupt) to encourage them to either vote for a particular party/ballot option or to dissuade them from voting at all.</p><p>For example, they may have targeted voters in the Rust Belt in America who are anxious about jobs to vote for Trump by sponsoring fake news articles highlighting how great his business record is. Or similarly, they could have targeted black Democrat voters in North Carolina to sow doubts in their minds about Clinton to discourage them from turning up on election day. These simple, highly targeted actions are enough to sway a whole country under the US electoral college system! The US election was potentially won by <a href="https://www.washingtonpost.com/graphics/politics/2016-election/swing-state-margins/">107,000 people</a> in swing states like Wisconsin! In the UK, the EU referendum was won by a mere 600,000 votes and a system like this could have been enough to sway just the right numbers of voters towards Brexit.</p><figure><img alt="" src="https://cdn-images-1.medium.com/max/1024/1*7HExX7h78-AzHDBbdOQifA.png" /><figcaption>Credit: The Washington Post</figcaption></figure><p>The big players are all mentioned and connected. Donald Trump and Steve Bannon (who apparently also headed one of the data companies), Nigel Farage, both the official Vote Leave campaign and the unofficial Leave.EU one… I’ll leave you to read the article for the gritty details!</p><p>I’ve always been somewhat apprehensive about big data and its potential to be used as a tool for evil but this article seems to make apparent that it is already happening, akin to an episode of Black Mirror or Minority Report… I am, however, a little shocked that the police and the electoral commission are not tackling this kind of abuse of technology head on. I don’t really expect GCHQ or MI5 to really do anything because they likely already use tools like this themselves (the article mentions that the very idea of psych-ops originates from the Royal Navy). The problem is that much of what these companies have done is not yet illegal, just highly unethical. The question is, are we just going to sit back and accept that democracy is now dead or are we going to do something about it? The UK general election is in just under a month and politicians will likely be using the very same tools to damage our democracy. The UK is particularly vulnerable because under our First-Past-The-Post system, only a few key swing seats actually matter while the rest rarely change parties. This means that elections can be won on the basis of a few hundred votes in targeted constituencies rather than the overall party share of the vote. I’m at a loss about what to do to prevent this because almost everyone is connected to Facebook and Google in some way…</p><p>Another related issue worrying me lately is that Facebook’s Mark Zuckerberg is <a href="http://www.salon.com/2017/05/03/is-mark-zuckerberg-suddenly-hinting-at-a-presidential-bid/">likely planning to run for President in 2020</a>. <a href="https://www.theguardian.com/technology/2017/may/02/facebook-executive-advertising-data-comment">Certain ex-Facebook employees</a> have already mentioned that as a company Facebook could have easily thrown the US election one way or the other (and perhaps did) by simply encouraging people to vote or not in certain districts through highly targeted notifications at the top of the feed. If Zuckerberg does run for President, he would have all these tools directly at his disposal and that is absolutely terrifying, no matter how good or bad you think he is personally.</p><p>We also can’t forget what has happened in the past when genocides of minorities were instigated and perpetrated by governments and powerful groups. It might sound a little melodramatic but I am genuinely concerned about both governments and powerful individuals having access to so much information about individuals because it might give authoritarian governments the power to do truly evil things.</p><p>The first thing you learn when working on big data is that humanity is only at the cusp of a data revolution. We’ve recorded more data in the past year than in the entire history of humanity and this is increasing almost exponentially (<a href="https://www.forbes.com/sites/bernardmarr/2015/09/30/big-data-20-mind-boggling-facts-everyone-must-read/#13da9b7b17b1">more on that here</a>). The problem is, this data isn’t distributed or shared equally amongst us all. A few big companies (Facebook, Google, Amazon, Verizon, etc) have privately collected more about us than anyone else. A few government agencies (NSA, GCHQ, other five eyes countries) know more about us than anyone else. We as citizens do not have access to the majority of what is collected about us. The Economist recently opined that “<a href="http://www.economist.com/news/leaders/21721656-data-economy-demands-new-approach-antitrust-rules-worlds-most-valuable-resource"><em>The world’s most valuable resource is no longer oil, but data</em></a>”. They suggest that we need new ways to tackle data-driven monopolistic and rent seeking behaviour (where an established entity uses its economic might to suppress others) and anti-trust cases which I don’t disagree with but it doesn’t really get to the heart of the issue, which is that the collection of big data actively harms our democracy as it currently stands.</p><figure><img alt="" src="https://cdn-images-1.medium.com/max/425/1*ZxCUuWIUSu5okhYWbGLuew.jpeg" /><figcaption><em>Photo by George Rex (CC-by-SA)</em>.</figcaption></figure><p>We all know about the dangers of a surveillance state and big brother, but George Orwell did not live in a world with 2 billion Facebook users liking millions of posts a second and visiting websites that track who they are, and 2.5 billion smartphone users, all happy to be or unwittingly location tracked 24/7. We’re sleep walking into a data-driven surveillance state where billionaires and governments work hand in hand — essentially modern-day fascism.</p><p>I’d love to know if you have any ideas on how to prevent this from becoming a reality! I certainly feel a little overwhelmed at the task, especially given the upcoming wave of A.I. and the increasing wealth inequality in our world…</p><p>If you live in the UK, the BBC just released <a href="http://www.bbc.co.uk/iplayer/episode/b08qgbc3/panorama-what-facebook-knows-about-you">a Panorama documentary</a> about Facebook and the power of big data… It’s a pretty good introduction to the new world we’re facing.</p><img src="https://medium.com/_/stat?event=post.clientViewed&referrerSource=full_rss&postId=6ddf3d12cb06" width="1" height="1" alt="">]]></content:encoded>
        </item>
        <item>
            <title><![CDATA[A Layman’s Guide to Computer Vision]]></title>
            <link>https://medium.com/data-science/a-laymans-guide-to-computer-vision-39b9291e5278?source=rss-ede5d822a083------2</link>
            <guid isPermaLink="false">https://medium.com/p/39b9291e5278</guid>
            <category><![CDATA[future-of-work]]></category>
            <category><![CDATA[artificial-intelligence]]></category>
            <category><![CDATA[machine-learning]]></category>
            <category><![CDATA[neural-networks]]></category>
            <category><![CDATA[towards-data-science]]></category>
            <dc:creator><![CDATA[Durand D'souza]]></dc:creator>
            <pubDate>Tue, 07 Mar 2017 20:01:51 GMT</pubDate>
            <atom:updated>2017-03-24T17:11:21.834Z</atom:updated>
            <cc:license>https://creativecommons.org/licenses/by-sa/4.0/</cc:license>
            <content:encoded><![CDATA[<figure><img alt="" src="https://cdn-images-1.medium.com/max/1024/1*sniXGf1bZHesUmN7ORtWYw.png" /></figure><p>I just discovered <a href="https://arxiv.org/abs/1703.01041v1">this newly published study</a> on arXiv today that I thought was super cool. It’s a fascinating glimpse into the future of machine learning and while I had been expecting this for a while, to finally see some solid research is amazing! It basically evolves a bunch of convolutional neural networks using a genetic algorithm to create an optimal network for image classification. To explain what the heck I’m talking about, read on!</p><figure><img alt="" src="https://cdn-images-1.medium.com/max/1024/1*ukC1xoQymw3HLLCdlYRnMA.png" /><figcaption>A bunch of animals.</figcaption></figure><p>Let’s say that we have a collection of photographs of various animals and we want to know what is in each photo. The most basic thing we can do with the help of our own eyes, our brain and our memory is to look at a photo, see that it is of a dog and label it as “dog”. For a computer to do the very same task is an incredibly tricky process.</p><p>A couple of decades ago, computer scientists tried to identify images programmatically by building a recipe to detect individual traits and put them together to predict what the photograph depicts. For example, a dog has fur, a long nose, big eyes, a long tongue, a tail, and so on. A cat has less fur, a rounder face, smaller eyes and a flatter nose. If you find these features in the photograph, then it must be a cat/dog/kangaroo. As you might imagine, this technique barely worked at all. If a photograph was taken at a different angle, the recipe would make no sense. Each animal would need its own particular recipe to be detected, different breeds or unkempt pets would be unidentifiable and it didn’t scale very well. The technique was expensive to develop and useless in practise.</p><figure><img alt="" src="https://cdn-images-1.medium.com/max/1024/0*x4HFSEMuoAM_POKd." /><figcaption>A car hiding in a tree</figcaption></figure><p>Fast forward a decade or so, and scientists tried to generalise this process a bit. Instead of detecting noses, they would detect circular shapes. Instead of fur, they would detect lines or particular patterns. Then combinations of these features would be used to be more predictive. This worked better, but it still involved manually programming in specific shapes and features to detect. It also wasn’t always successful and sometimes failed impressively as above.</p><p>Then in 1998, a completely new technique called Convolutional Neural Networks (CNNs) <a href="http://vision.stanford.edu/cs598_spring07/papers/Lecun98.pdf">came out</a> which tried to mimic how our brains process images. Instead of manually choosing features to be detected, the features would be automatically “learned” by a computer by feeding it a lot of images and the correct labels. The computer program would then calculate which features are most important and use them to classify photos. These features are basically simple mathematical filters that the image is passed through to simplify its structure into key components. By using multiple layers of features, more complex objects can be detected. Below, you can see how such a program might work. In the first layer, basic shapes are detected. In the second, these shapes are combined to build more complex ones, such as eyes and noses. And finally, in the third layer, these are combined into higher level objects, such as human faces!</p><figure><img alt="" src="https://cdn-images-1.medium.com/max/754/0*relYRmjE3RYCY0Sf." /><figcaption>Feature map in a modern CNN</figcaption></figure><p>While the CNN developed in 1998 was very successful, especially at tasks such as handwriting recognition, it did require a huge amount of processing power and a large set of training data, two requirements which could not be easily fulfilled in 1999. So for more than a decade, this technique was effectively shelved while people continued to manually define features.</p><p>And then finally in 2012, researchers at the Uni. of Toronto created <a href="http://papers.nips.cc/paper/4824-imagenet-classification-with-deep-convolutional-neural-networks">AlexNet</a>. It used the same techniques of the original CNN, with a few changes, but on a much larger set of images. Instead of a few thousand, AlexNet was trained on 15 million images. And instead of just a few filters, it computed hundreds. It blew the competition out of the park when it was released. All programmers now had to do was design the basic flow of the network and choose the building blocks and the neural network would figure out the rest.</p><p>In the span of 30 years, computer vision technology improved at a snail’s pace, but AlexNet changed all that. Before 2012, <em>1 in every 4</em> images was incorrectly identified. AlexNet reduced that down to <em>1 in every 7</em>. Since then, the error has come down to <em>1 in every 25</em> images (eg. in Google’s Inception network). That accuracy is actually better than the vast majority of humans! And that brings us to this paper.</p><figure><img alt="" src="https://cdn-images-1.medium.com/max/1024/0*lxFzfqV5gexWkqxn." /><figcaption>Google’s Inception V3 network. State-of-the-art in image classification, for now.</figcaption></figure><p>All the improvements in the last five years have been down to tweaking the neural networks slightly, either by adding new mathematical functions, changing the order and combination of filters or increasing the level of detail captured by filters. These “macroparameters” can be tweaked endlessly to get the best results but they require a bit of intuition to get right. The researchers in this paper decided to automate that last step.</p><figure><img alt="" src="https://cdn-images-1.medium.com/max/492/1*n1nWfw-qsp99E2ngefVh5A.png" /><figcaption>Relevant XKCD (<a href="https://www.google.co.uk/url?sa=t&amp;rct=j&amp;q=&amp;esrc=s&amp;source=web&amp;cd=1&amp;cad=rja&amp;uact=8&amp;ved=0ahUKEwj_nP-RlMXSAhUKKcAKHdoqDKwQFggcMAA&amp;url=https%3A%2F%2Fxkcd.com%2F534%2F&amp;usg=AFQjCNEpuTn8mpgWgifXuareoY2B5Q2lEw&amp;sig2=E-dxVYYeScGMVarSfXCO3g">CC-by-SA-NC Randall Munroe</a>)</figcaption></figure><p>Instead of tediously designing a new network and manually combining different functions and filters, they simply gave a genetic machine learning algorithm a task — to minimise the identification error — and gave it the building blocks. They then let it run for a few weeks on a fast computer. It goes ahead, builds a basic neural network and computes the error in its image recognition. It then makes a few changes, and computes a new error. If the error is lower, it adopts that design, and so on and so forth. In fact, it improves much like biological evolution, through mutation, reproduction and survival.</p><p>If you actually made it all the way to the end of this very long post, then thank you for reading! You’ll no doubt still be wondering why I find this so cool. And the reason is that not only does this paper shine a spotlight on how far we (well… brainy guys and gals) have come with artificial intelligence, but also how our world will be shaped by it in the future. We are at the point where a stupid monkey like me can play around with technology that confounded thousands of researchers for decades. Someone with a thousand pounds and no prior knowledge of artificial intelligence can achieve what took millions of research hours in the past. All we need is a data set and a clever idea and we can let AI do the hard work! I think that is both bloody impressive and quite frightening! We’re not quite there yet but there will come a point when AI will replace the computer scientists who created them so it would be wise if started planning for that future <a href="https://www.bostonglobe.com/ideas/2016/02/24/robots-will-take-your-job/5lXtKomQ7uQBEzTJOXT7YO/story.html">now</a>.</p><p>In the not-too-distant future, I can imagine a scenario where anyone who wanted to make their own movie could simply write a movie script with some cues and stylistic elements, pass it to an AI who then automatically creates the soundtrack, synthesises the speech, directs a bunch of 3d generated models, adds some special effects and renders a complete photo-realistic movie. If something wasn’t quite right, you could go in and tweak it. When the film camera was invented in the 1880s, people didn’t predict how ubiquitous it would become. When the electric guitar was invented, engineers tried their hardest to remove the distortions it created, yet rock music today is built on that very sound base. I may well be wrong about the future of AI but I can’t wait to see what happens! <em>*hopefully not skynet*</em></p><iframe src="https://cdn.embedly.com/widgets/media.html?src=https%3A%2F%2Fwww.youtube.com%2Fembed%2FLY7x2Ihqjmc%3Ffeature%3Doembed&amp;display_name=YouTube&amp;url=https%3A%2F%2Fwww.youtube.com%2Fwatch%3Fv%3DLY7x2Ihqjmc&amp;image=https%3A%2F%2Fi.ytimg.com%2Fvi%2FLY7x2Ihqjmc%2Fhqdefault.jpg&amp;key=a19fcc184b9711e1b4764040d3dc5c07&amp;type=text%2Fhtml&amp;schema=youtube" width="854" height="480" frameborder="0" scrolling="no"><a href="https://medium.com/media/560e69a5556ca45339976138712c482e/href">https://medium.com/media/560e69a5556ca45339976138712c482e/href</a></iframe><p><strong>Further reading, if your interest is piqued:</strong></p><ul><li><a href="https://www.youtube.com/watch?v=u6aEYuemt0M"><em>This fantastic talk</em></a><em> by Andrej Karpathy, where I got most of my material from.</em></li><li><a href="https://youtu.be/40riCqvRoMs">A TED talk by Fei Fei Li</a>, who established the ImageNet database</li><li><a href="https://aiexperiments.withgoogle.com/"><em>AI experiments </em></a><em>by Google</em></li><li><em>Siraj Raval’s over-the-top </em><a href="https://www.youtube.com/channel/UCWN3xxRkmTPmbKwht9FuE5A"><em>Youtube channel</em></a></li><li><a href="https://www.youtube.com/channel/UCbfYPyITQ-7l4upoX8nvctg"><em>Two Minute Papers</em></a><em>, which showcases some of the coolest AI stuff out there!</em></li><li><a href="http://colah.github.io/posts/2014-07-Conv-Nets-Modular/"><em>Chris Olah’s blog</em></a><em> on neural networks</em></li></ul><p><strong>Animal photographs:</strong></p><ul><li>Meerkats: <a href="https://www.pexels.com/u/mikebirdy/">CC-0 Mike Birdy</a></li><li>Dogs &amp; Horse: <a href="https://www.pexels.com/u/hilaryh/">CC-0 Hilary Halliwell</a></li><li>Leopard: <a href="http://www.pixnio.com/fauna-animals/cheetahs-leopards-jaguars-panthers-pictures/leopard-wild-cat-animal-animal-photography-cat">CC-0</a></li><li>Goose: <a href="http://www.pixnio.com/fauna-animals/birds/goose-pictures/goose-plumage-animal-photography-bird">CC-0</a></li><li>Macaque: <a href="https://commons.wikimedia.org/wiki/File:Macaca_nigra_self-portrait_large.jpg">Public Domain</a></li><li>Duck: <a href="https://www.pexels.com/u/martindickson/">CC-0 Martin Dickinson</a></li><li>Spider: <a href="https://en.wikipedia.org/wiki/Wikipedia:Featured_pictures/Animals/Arachnids#/media/File:Phidippus_audax_male.jpg">CC-by-SA Thomas Shahan</a></li><li>Jaguar: <a href="https://www.flickr.com/photos/ucumari/3653240665">CC-by-SA-ND Valerie</a></li><li>Dog: <a href="https://www.pexels.com/u/pixabay/">CC-0 Pixabay</a></li><li>Jaguar: <a href="https://www.pexels.com/photo/africa-zoo-tiger-cat-9322/">CC-0 Skitterphoto</a></li></ul><p><em>Feel free to share &amp; modify this article under a </em><a href="https://creativecommons.org/licenses/by/4.0/"><em>Creative Commons Share-Alike</em></a><em> licence and let me know if there are corrections to be made!</em></p><img src="https://medium.com/_/stat?event=post.clientViewed&referrerSource=full_rss&postId=39b9291e5278" width="1" height="1" alt=""><hr><p><a href="https://medium.com/data-science/a-laymans-guide-to-computer-vision-39b9291e5278">A Layman’s Guide to Computer Vision</a> was originally published in <a href="https://medium.com/data-science">TDS Archive</a> on Medium, where people are continuing the conversation by highlighting and responding to this story.</p>]]></content:encoded>
        </item>
    </channel>
</rss>