This video is about how I built a deep reinforcement learning based visual maze solving networkusing Keras. This is a followup to my second live stream (linked below) where I tried doing this and ran into some issues. I explain the whole system is detail and specifically go over a lot of the mistakes I made that others are likely to make as well. Code Repo: https://github.com/safijari/jack-of-some-rl-journey Slides from David Silver's Excellent Tutorial: https://icml.cc/2016/tutorials/deep_rl_tutorial.pdf Paper referenced: https://arxiv.org/pdf/1509.06461.pdf SOME OF MY OTHER VIDOES: ○ Deep RL Stream: https://www.youtube.com/watch?v=psDlXfbe6ok ○ Vanilla Q Learning Stream: https://www.youtube.com/watch?v=psDlXfbe6ok ○ Explaining RL to a baby: https://www.youtube.com/watch?v=GFIKtFSl1XQ ○ 5 Common Python Mistakes: https://www.youtube.com/watch?v=fMRzuwlqfzs ○ Making Python fast: https://www.youtube.com/watch?v=XW32lPcWOxg Twitter: twitter.com/safijari Patreon: https://www.patreon.com/jackofsome ... https://www.youtube.com/watch?v=JwG6J-MHFfY

In this video I describe the installation, configuration, and usage of my primary text editor: Spacemacs (http://spacemacs.org/). This editor is a kit for the venerable Emacs text editor and is very suitable for programming, especially when dealing with large complex code bases. Disclaimer: This tutorial assumes you know the basics of navigating code in Vim. If you do not, consider watching a video on the subject (this video https://www.youtube.com/watch?v=lxET5r3Xc3g is pretty good). Note: it was pointed out to me that I forgot to go over how to create a new file. You can do it vim style ( :e filepath ) or if you try to visit a non existing file in the SPC f f menu it'll create a new file for you. Emacs installation in ... Ubuntu: https://bit.ly/2UXsAr4 Mac OS: https://bit.ly/2GOcNCi Windows: https://bit.ly/2PAlqmF Twitter: https://twitter.com/safijari Laser Groove Kevin MacLeod (incompetech.com) Licensed under Creative Commons: By Attribution 3.0 License http://creativecommons.org/licenses/by/3.0/ Thumbnail from: https://spin.atomicobject.com/2016/08/30/introduction-to-spacemacs/ ... https://www.youtube.com/watch?v=fdLCuJcS2Aw

I demonstrate how to learn a new programming language by teaching myself Julia. This is a long video so I suggest chunking your view time and using the following links to navigate. 00:45 List of Topics 04:40 Installation/toolchain 10:15 Basic Syntax 20:54 Arrays/Lists 27:50 Tuples 29:20 Dictionaries/Sets 32:41 Control flow (if/else) 33:22 Loops 35:47 Functions (+ first class) 42:00 Types, Structs 52:00 Package Management (Pkg) 55:30 Notebooks, plotting, deployment 1:01:00 Macros 1:03:23 Threading 1:05:30 Spring mass damper example (more threading) 1:17:36 Concluding thoughts Twitter: https://twitter.com/safijari #julia #programming #learning ... https://www.youtube.com/watch?v=TNoShNPoEak

In this video I introduce Numba which can make your python code 100x faster. Numba is a just in time compiler for a subset of Python and Numpy. The first half of the video is dedicated to a basic intro and to highlighting a number of very common mistakes people make when using Numba. The remaining video show how to use Numba in a real world-ish simulation problem and shows the code running 1000x faster with Numba in both single and multithreaded cases, and concludes with a "reading list" for learning more about Numba. Twitter: https://twitter.com/safijari Find the notebook here: https://gist.github.com/safijari/fa4eba922cea19b3bc6a693fe2a97af7 MY OTHER VIDOES: ○ A.I. Learns to play Snake https://www.youtube.com/watch?v=i0Pkgtbh1xw ○ 5 Common Python Mistakes: https://www.youtube.com/watch?v=fMRzuwlqfzs ○ 5 Amazing Python Libraries: https://www.youtube.com/watch?v=eILeIEE3C8c ○ Making Python fast: https://www.youtube.com/watch?v=XW32lPcWOxg ○ Learning programming language Julia: https://www.youtube.com/watch?v=TNoShNPoEak Deeper topics to discover here https://numba.pydata.org/numba-doc/dev/user/5minguide.html#other-things-of-interest Supported python and numpy features https://numba.pydata.org/numba-doc/dev/reference/pysupported.html https://numba.pydata.org/numba-doc/dev/reference/numpysupported.html Important differences from python https://numba.pydata.org/numba-doc/dev/reference/pysemantics.html Defining types to compile at definition time: http://numba.pydata.org/numba-doc/latest/user/jit.html#eager-compilation Function factories https://numba.pydata.org/numba-doc/dev/user/generated-jit.html Experimental version of jitted classes https://numba.pydata.org/numba-doc/dev/user/jitclass.html Debugging https://numba.pydata.org/numba-doc/dev/user/troubleshoot.html Dealing with types https://numba.pydata.org/numba-doc/dev/reference/types.html Ahead of time compilation for deployment https://numba.pydata.org/numba-doc/dev/user/pycc.html Using approximate fastmath https://numba.pydata.org/numba-doc/dev/user/performance-tips.html#fastmath Deeper control of threading via tbb and/or omp https://numba.pydata.org/numba-doc/dev/user/threading-layer.html Easily put your computation on a GPU! https://numba.pydata.org/numba-doc/dev/cuda/index.html https://numba.pydata.org/numba-doc/dev/roc/index.html F.A.Qs https://numba.pydata.org/numba-doc/dev/user/faq.html #numba #programming #python ... https://www.youtube.com/watch?v=x58W9A2lnQc