__[slides](https://yadi.sk/i/dJKR4CI43PfRjD)__

* Russian [lecture](https://yadi.sk/i/X6rS31O7r6Aco), [seminar](https://yadi.sk/i/LZppDeV9r8H4Q)

* English lectures: [word embeddings](https://www.youtube.com/watch?v=ERibwqs9p38), [text convolutions](https://www.youtube.com/watch?v=nzSPZyjGlWI)

* Deep learning for music - [blog post](http://benanne.github.io/2014/08/05/spotify-cnns.html)

* Wavenet - convolutional generative model for music - [blog post](https://deepmind.com/blog/wavenet-generative-model-raw-audio/)

This week's practice is just as usual: pick one of two notebooks (theano or tf) and follow instructions inside.

However, there are two alternative assignments (both in theano) that you can do _instead of_ main assignment:

* 1d convolutions for prohibited content filtering

* 1d convolutions for music processing