In this video, I explain the basics of recurrent neural networks. Then we code our own RNN in 80 lines of python (plus white-space) that predicts the sum of two binary numbers after training.
Code for this video:
https://github.com/llSourcell/recurrent_neural_net_demo
I created a Slack channel for us, sign up here:
https://wizards.herokuapp.com/
Thank @iamtrask for a great RNN article:
https://iamtrask.github.io/2015/11/15/anyone-can-code-lstm/
and this piece by Karpathy on RNN's deserves some sort of award:
http://karpathy.github.io/2015/05/21/rnn-effectiveness/
Another great RNN article:
http://nikhilbuduma.com/2015/01/11/a-deep-dive-into-recurrent-neural-networks/
Tensorflow RNNs:
https://www.tensorflow.org/versions/r0.10/tutorials/recurrent/index.html
Thanks so much for watching my videos, I do this stuff for you guys. I'm about to hit 10K subscribers soon. If and when I do, I'm going to start working on a machine learning music video to celebrate! With better production quality than my last two!
I recently created a Patreon page. If you like my videos, feel free to help support my effort here!:
https://www.patreon.com/user?ty=h&u=3191693
Much more to come so please subscribe, like, and comment.
Follow me:
Twitter: https://twitter.com/sirajraval
Facebook: https://www.facebook.com/sirajology Instagram: https://www.instagram.com/sirajraval/ Instagram: https://www.instagram.com/sirajraval/
