Machine Learning is Fun! Part 2

<p><strong><em>Update:</em></strong><em>&nbsp;This article is part of a series. Check out the full series:&nbsp;</em><a href="https://medium.com/@ageitgey/machine-learning-is-fun-80ea3ec3c471" rel="noopener"><em>Part 1</em></a><em>,&nbsp;</em><a href="https://medium.com/@ageitgey/machine-learning-is-fun-part-2-a26a10b68df3" rel="noopener"><em>Part 2</em></a><em>,&nbsp;</em><a href="https://medium.com/@ageitgey/machine-learning-is-fun-part-3-deep-learning-and-convolutional-neural-networks-f40359318721" rel="noopener"><em>Part 3</em></a><em>,&nbsp;</em><a href="https://medium.com/@ageitgey/machine-learning-is-fun-part-4-modern-face-recognition-with-deep-learning-c3cffc121d78" rel="noopener"><em>Part 4</em></a><em>,&nbsp;</em><a href="https://medium.com/@ageitgey/machine-learning-is-fun-part-5-language-translation-with-deep-learning-and-the-magic-of-sequences-2ace0acca0aa" rel="noopener"><em>Part 5</em></a><em>,&nbsp;</em><a href="https://medium.com/@ageitgey/machine-learning-is-fun-part-6-how-to-do-speech-recognition-with-deep-learning-28293c162f7a" rel="noopener"><em>Part 6</em></a><em>,&nbsp;</em><a href="https://medium.com/@ageitgey/abusing-generative-adversarial-networks-to-make-8-bit-pixel-art-e45d9b96cee7" rel="noopener"><em>Part 7</em></a><em>&nbsp;and&nbsp;</em><a href="https://medium.com/@ageitgey/machine-learning-is-fun-part-8-how-to-intentionally-trick-neural-networks-b55da32b7196" rel="noopener"><em>Part 8</em></a><em>!&nbsp;</em>You can also read this article in&nbsp;<a href="https://medium.com/botsupply/il-machine-learning-%C3%A8-divertente-parte-2-dec556e4855d" rel="noopener"><em>Italiano</em></a><em>,&nbsp;</em><a href="https://medium.com/@lfcj/machine-learning-es-divertido-parte-2-b12f488675c5" rel="noopener"><em>Espa&ntilde;ol</em></a><em>,&nbsp;</em><a href="https://medium.com/@alexis.anzieu/samuser-avec-le-machine-learning-part2-41974ee1f586" rel="noopener"><em>Fran&ccedil;ais</em></a><em>,&nbsp;</em><a href="https://medium.com/@atakanyenel/makine-%C3%B6%C4%9Frenimi-e%C4%9Flencelidir-2-k%C4%B1s%C4%B1m-6b464cbdf40c" rel="noopener"><em>T&uuml;rk&ccedil;e</em></a><em>,&nbsp;</em><a href="http://algotravelling.com/ru/%D0%BC%D0%B0%D1%88%D0%B8%D0%BD%D0%BD%D0%BE%D0%B5-%D0%BE%D0%B1%D1%83%D1%87%D0%B5%D0%BD%D0%B8%D0%B5-%D1%8D%D1%82%D0%BE-%D0%B2%D0%B5%D1%81%D0%B5%D0%BB%D0%BE-2/" rel="noopener ugc nofollow" target="_blank"><em>Русский</em></a><em>,&nbsp;</em><a href="https://medium.com/@jongdae.lim/%EA%B8%B0%EA%B3%84-%ED%95%99%EC%8A%B5-machine-learning-%EC%9D%80-%EC%A6%90%EA%B2%81%EB%8B%A4-part-2-b35f3d327761" rel="noopener"><em>한국어&nbsp;</em></a><a href="https://medium.com/machina-sapiens/aprendizagem-de-m%C3%A1quina-%C3%A9-divertido-parte-2-7c00d034e1d5" rel="noopener"><em>Portugu&ecirc;s</em></a><em>,&nbsp;</em><a href="https://zerotohero.ir/article/machine-learning/%DB%8C%D8%A7%D8%AF%DA%AF%DB%8C%D8%B1%DB%8C-%D9%85%D8%A7%D8%B4%DB%8C%D9%86-%D8%A8%D9%87-%D8%B2%D8%A8%D8%A7%D9%86-%D8%B3%D8%A7%D8%AF%D9%87-%D8%A8%D8%AE%D8%B4-%D8%AF%D9%88%D9%85" rel="noopener ugc nofollow" target="_blank">فارسی</a>,&nbsp;<a href="https://viblo.asia/p/machine-learning-that-thu-vi-2-tao-sach-van-hoc-va-game-mario-WAyK81o9ZxX" rel="noopener ugc nofollow" target="_blank"><em>Tiếng Việt</em></a>&nbsp;<em>or&nbsp;</em><a href="https://zhuanlan.zhihu.com/p/24344720" rel="noopener ugc nofollow" target="_blank"><em>普通话</em></a><em>.</em></p> <p><strong><em>Giant update:</em></strong><em>&nbsp;</em><a href="https://www.machinelearningisfun.com/get-the-book/" rel="noopener ugc nofollow" target="_blank"><em>I&rsquo;ve written a new book based on these articles</em></a><em>! It not only expands and updates all my articles, but it has tons of brand new content and lots of hands-on coding projects.&nbsp;</em><a href="https://www.machinelearningisfun.com/get-the-book/" rel="noopener ugc nofollow" target="_blank"><em>Check it out now</em></a><em>!</em></p> <p>In&nbsp;<a href="https://medium.com/@ageitgey/machine-learning-is-fun-80ea3ec3c471" rel="noopener">Part 1</a>, we said that Machine Learning is using generic algorithms to tell you something interesting about your data without writing any code specific to the problem you are solving. (If you haven&rsquo;t already read&nbsp;<a href="https://medium.com/@ageitgey/machine-learning-is-fun-80ea3ec3c471" rel="noopener">part 1</a>, read it now!).</p> <p>This time, we are going to see one of these generic algorithms do something really cool<em>&nbsp;&mdash;&nbsp;</em>create video game levels that look like they were made by humans. We&rsquo;ll build a neural network, feed it existing Super Mario levels and watch new ones pop out!</p> <p><a href="https://medium.com/@ageitgey/machine-learning-is-fun-part-2-a26a10b68df3"><strong>Click Here</strong></a></p>