{"id":983,"date":"2018-11-15T02:50:35","date_gmt":"2018-11-14T23:50:35","guid":{"rendered":"http:\/\/kusuaks7\/?p=588"},"modified":"2021-11-25T08:49:58","modified_gmt":"2021-11-25T08:49:58","slug":"learning-ai-if-you-suck-at-math-part-1","status":"publish","type":"post","link":"https:\/\/www.experfy.com\/blog\/ai-ml\/learning-ai-if-you-suck-at-math-part-1\/","title":{"rendered":"Learning AI if You Suck at Math\u200a\u2014\u200aPart 1\u200a"},"content":{"rendered":"

Ready to learn Artificial Intelligence? Browse courses<\/a>\u00a0like\u00a0 Uncertain Knowledge and Reasoning in Artificial Intelligence<\/a> developed by industry thought leaders and Experfy in Harvard Innovation Lab.<\/em><\/strong><\/p>\n

If you\u2019re like me, you\u2019re fascinated with AI.<\/p>\n

Maybe you\u2019d love to dig deeper and get an image recognition program running in\u00a0TensorFlow<\/a>\u00a0or\u00a0Theano<\/a>? Perhaps you\u2019re a kick-ass developer or systems architect and you know computers incredibly well but there\u2019s just one little problem:<\/p>\n

You suck at math.<\/p>\n

That\u2019s all right! I share your dirty little secret and I have some books and websites that will really help you get rolling fast.<\/p>\n

Like many folks, my love of intelligent machines didn\u2019t come from calculus class. It sprang from science fiction. I remember reading\u00a0\u201cI, Robot\u201d<\/a>\u00a0one beautiful summer evening and imagining ways to trip up Asimov\u2019s\u00a0Three Rules of Robotics<\/a>. As I watched masterpieces like\u00a02001: A Space Odyssey<\/a>\u00a0and\u00a0Ghost in the Shell<\/a>, it seemed that any day a\u00a0gestalt consciousness might surge up from the glittering sea of information<\/a>\u00a0and declare itself sentient. When I grew up and started publishing\u00a0my own sci-fi<\/a>\u00a0I imagined AI as a pervasive, ambient force that\u2019s always there, like electricity, touching every aspect of life.<\/p>\n

Turns out, we have a few things to figure out before General AI can pop from the primordial digital goo. Mostly nothing ever came of the early AI promises in the 80\u2019s and 90\u2019s. Hype never lived up to reality and\u00a0AI winter followed AI winter<\/a>.<\/p>\n

All that changed in the last few years with the sudden success of\u00a0Deep Learning.<\/p>\n

Maybe you saw the story in the New York Times that showed how\u00a0Google transformed its translation services\u00a0almost overnight<\/a>\u00a0delivering accuracy that rivaled professional translators? In a mere nine months, they outpaced what the platform managed in the seven previous years\u00a0combined<\/em>.<\/p>\n

Perhaps you read about\u00a0the kid who built a self-driving car in his freaking garage<\/a>\u00a0with open source tools? You might have also seen this amazing slide below that shows how DL ripped through the\u00a0Imagenet image recognition competition<\/a>\u00a0in just a few years, dropping the error rate from 25% to something that performs better than humans in 2017.<\/p>\n

<\/figure>\n

No matter how you cut it, AI solves big, intractable problems that have eluded us for decades. We know how to drive a car yet we can\u2019t tell machines how to do it. But we can let machines figure it out for themselves. For once a technology coming out of Silicon Valley is not just hype. It\u2019s real. AI is hot for good reasons.<\/p>\n

Top AI researchers are\u00a0earning more than NFL starting quarterbacks<\/a>\u00a0and you want to get in on the gold rush. Then again, you probably saw\u00a0the big scary stories that AI will eat all the jobs<\/a>\u00a0and as a traditional software engineer or sys-admin you want to make sure you have the skills to compete in an AI-centric world. No problem. There are tons of tutorials out there. You just have to get started, right?<\/p>\n

Then you get to a passage like the one below in\u00a0Ian Goodfellow\u2019s seminal Deep Learning book<\/a>\u00a0and you have no idea what he is talking about at all.<\/p>\n

<\/figure>\n

Uh-oh.<\/p>\n

The problem is you have to understand a nested layer of logic, terms, symbols and ideas that are all interrelated but you have no foundation for any of it. So it basically sounds like an alien language. You probably understand all the text leading up to it but the rest is just gibberish. It can turn really disheartening fast.<\/p>\n

But have no fear! All is not lost.<\/p>\n

I\u2019m here to help you wade through the swamp with some books that will get you crunching numbers like a savant. All right, well maybe you won\u2019t be\u00a0Daniel Tammet<\/a>, but you can put aside those painful memories of times-table memorization and get cranking. You CAN learn math as an adult.<\/p>\n

I\u2019ve tried to read a number of AI texts and tutorials. I understand the concepts intuitively. They make perfect sense to me. It\u2019s just that when I see a string of symbols my brain glazes over and I have no idea what I\u2019m reading. As a systems architect for much of my life I didn\u2019t need much math. There are IP subnet cheat sheets and as long as I knew how far electricity could reasonably travel along the length of cables I could cut them and crimp them appropriately. For most of my life, I needed to understand how systems get setup, how they work together and how they stay running. Systems administration is very boolean. It either works or it doesn\u2019t. But AI and math works on a different side of the brain.<\/p>\n

What I needed were some primers written for adults that treat you like one. I also want books that answer questions about\u00a0why<\/em>\u00a0math works. In school, your reason for learning was probably \u201cshut up and do it or else.\u201d But as an adult you need more. You want to know how things work too.<\/p>\n

<\/figure>\n

The very first book you need mathematics: A Very Short Introduction<\/strong><\/a>\u00a0by Timothy Gowers.<\/strong><\/p>\n

This book breaks down the \u201cwhy\u201d of math beautifully. It relates the subject to the real world, gets into the philosophy and then quickly leaves the philosophy behind because you don\u2019t really need to understand whether fractions actually exist in nature or at the Platonic level. Instead, Timothy helped me understand that math is an abstraction layer. It breaks problems down into simpler, cleaner steps. The complexity of working out a model that precisely simulates particle interaction in a box would need to take into account an insane amount of real world physics properties like magnetic interference, gravity, the force of the collision, the particles initial direction and speed as well as much, much more. It turns out life is a complex series of algorithms. But here\u2019s the trick. In practice you don\u2019t need a perfect model. Instead, math looks to break the problem down into its\u00a0essential<\/em>\u00a0components. What are the critical factors? Math gives you a general abstraction of the problem that can work with other problem sets as well. In essence, the numbers themselves don\u2019t matter all that much. They are just variables. Math boils down to variables and rules. You can learn those variables and rules!<\/p>\n

<\/canvas><\/figure>\n

While you\u2019re reading the book you will want to have\u00a0this website\u2019s handy dandy guide to the major math symbols<\/a>. You can also pick up\u00a0this super concise guide for engineers called\u00a0Mathematical Notation by Edward R. Scheinerman<\/strong><\/a>. If you\u2019re like me, you\u2019ll have to see these symbols hundreds of times before they stick. You may find yourself forgetting various symbols the second you turn the page! Not to worry. This cheat sheet is perfect. Take a deep breath, slow down and go through the symbols one by one until you start to understand that string of crazy looking glyphs. Even if you have to look up every symbol a thousand times do it! There are no shortcuts to learning in life. You just have to do the work.<\/p>\n

Now there are two other strong contenders for getting your math foundation built.\u00a0The first is\u00a0<\/strong>Mathematics for the Nonmathematician<\/strong><\/a>\u00a0by Morris Kline. The second is the\u00a0<\/strong>No Bullshit Guide to Math and Physics<\/strong><\/a>\u00a0by Ivan Savov.\u00a0<\/strong>Each appeals to a different mindset. I prefer the very short intro because it gets down to brass tacks quickly and still manages to stay very relate-able. The \u201cMath for Nonmathematicians\u201d book is much longer and goes into more detail about the history of math and how it works in the world. Some people will really enjoy that approach. The \u201cNo Bullshit Guide\u201d is quick and gets right into the equations fast with no answer as to why anything works the way it does. It\u2019s basically a primer on the rules. That will appeal to folks who have less of a philosophical bent.<\/p>\n

<\/figure>\n

The next book you will want is\u00a0<\/strong>Algebra Unplugged<\/strong><\/a>\u00a0by Jim Loats and Kenn Amdahl.<\/strong>\u00a0Now there are a few typos in the book but I don\u2019t find them all that distracting. I appreciate the book\u2019s approach to gentle learning that quickly accelerates. Some people get worked into a lather over typos but you\u2019ve got bigger challenges to worry about. You\u2019re trying to learn math when your brain isn\u2019t quite as plastic as it once was in your youth! So let the typos go and see the big picture here. This book will really help you get moving in the right direction.<\/p>\n

After you\u2019ve got the math down you\u2019ll want to dig into\u00a0<\/strong>Make Your Own Neural Network<\/strong><\/a>\u00a0by Tariq Rashid.<\/strong>\u00a0It also has some typos, but there is a\u00a0great Github repo<\/a>\u00a0with updates that fixes most of them. This book is incredibly gentle and intuitive. It seems to anticipate your objections and fears the second you have them! The author is uncanny in how he spots your resistance as it happens. The book walks through only the math you need for neural networks specifically. It then works through Python, assuming you know nothing about programming. Finally, it gets you coding your own neural network from scratch. Now while there are certainly tools out there that will work better for professional programs, it helps to try your hand at your own first, so you understand the basics.<\/p>\n

<\/canvas><\/figure>\n

After that book, you\u2019ll want to start browsing the web. There are awesome new tutorials coming out every single day.\u00a0Maybe check out\u00a0<\/strong>Tensorflow for Poets<\/strong><\/a>\u00a0or\u00a0<\/strong>Recurrent Neural Networks for Artists<\/strong><\/a>.<\/strong><\/p>\n

Medium itself is awesome for learning about AI.\u00a0For example, check out\u00a0<\/strong>this article on a roundup of various classes you can take<\/strong><\/a>\u00a0to get deeper than you could on your own.<\/strong> Then again, maybe you\u2019re not the class taking type and prefer to work through things yourself? No problem.\u00a0Instead, check out\u00a0<\/strong>this eight part series from AI researcher Arthur Juliani<\/strong><\/a>. There is also this one called\u00a0<\/strong>Machine Learning is Fun<\/strong><\/a>, another great series right here on your favorite site.<\/strong><\/p>\n

Lastly, you may want to move on to a more advanced book, confident in your ability to understand more challenging concepts. That book is the one I already mentioned earlier,\u00a0<\/strong>Ian Goodfellow\u2019s Deep Learning book<\/strong><\/a>, which you can read online or\u00a0<\/strong>grab yourself a hard copy on Amazon<\/strong><\/a>.<\/strong><\/p>\n

That\u2019s all for now. Feel free to add your own books in the comments. Everyone learns a little differently and there are bound to be other books worth sharing.<\/p>\n","protected":false},"excerpt":{"rendered":"

You’re fascinated with AI. Maybe you’d love to dig deeper and get an image recognition program running in TensorFlow or Theano? Perhaps you’re a developer or systems architect and you know computers incredibly well but there’s just one little problem: You suck at math. That’s all right! Here are some little secrets that help you get rolling fast. No matter how you cut it, AI solves big, intractable problems that have eluded us for decades. AI is hot for good reasons. <\/p>\n","protected":false},"author":393,"featured_media":24207,"comment_status":"open","ping_status":"open","sticky":false,"template":"single-post-2.php","format":"standard","meta":{"content-type":"","footnotes":""},"categories":[183],"tags":[97],"ppma_author":[2209],"class_list":["post-983","post","type-post","status-publish","format-standard","has-post-thumbnail","hentry","category-ai-ml","tag-artificial-intelligence"],"authors":[{"term_id":2209,"user_id":393,"is_guest":0,"slug":"daniel-jeffries","display_name":"Daniel Jeffries","avatar_url":"https:\/\/secure.gravatar.com\/avatar\/?s=96&d=mm&r=g","user_url":"","last_name":"Jeffries","first_name":"Daniel","job_title":"","description":"Dan Jeffries is an author, engineer and serial entrepreneur. During his two decades in the computer industry, he's covered a broad range of tech from Linux to networks and virtualization. "}],"_links":{"self":[{"href":"https:\/\/www.experfy.com\/blog\/wp-json\/wp\/v2\/posts\/983","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/www.experfy.com\/blog\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/www.experfy.com\/blog\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/www.experfy.com\/blog\/wp-json\/wp\/v2\/users\/393"}],"replies":[{"embeddable":true,"href":"https:\/\/www.experfy.com\/blog\/wp-json\/wp\/v2\/comments?post=983"}],"version-history":[{"count":3,"href":"https:\/\/www.experfy.com\/blog\/wp-json\/wp\/v2\/posts\/983\/revisions"}],"predecessor-version":[{"id":27834,"href":"https:\/\/www.experfy.com\/blog\/wp-json\/wp\/v2\/posts\/983\/revisions\/27834"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/www.experfy.com\/blog\/wp-json\/wp\/v2\/media\/24207"}],"wp:attachment":[{"href":"https:\/\/www.experfy.com\/blog\/wp-json\/wp\/v2\/media?parent=983"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/www.experfy.com\/blog\/wp-json\/wp\/v2\/categories?post=983"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/www.experfy.com\/blog\/wp-json\/wp\/v2\/tags?post=983"},{"taxonomy":"author","embeddable":true,"href":"https:\/\/www.experfy.com\/blog\/wp-json\/wp\/v2\/ppma_author?post=983"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}