My personal favorite, Statistical Mechanics and Computations.[1]. Excelled introduction to MCMC methods, lots and lots of python programs and filmed against a green screen.
Obligatory, Stanford CS231n: Convolutional Neural Networks for Visual Recognition [2] The assignments are excellent and will let you implement a deephish network from practically scratch, before diving into modern frameworks and applications.
Obligatory, Stanford CS231n: Convolutional Neural Networks for Visual Recognition [2] The assignments are excellent and will let you implement a deephish network from practically scratch, before diving into modern frameworks and applications.
[1]: https://www.coursera.org/learn/statistical-mechanics [2]: http://cs231n.stanford.edu/index.html