The best part about this ML course is that all assignments are in Torch (a deep learning framework in Lua) for which Andrej Karpathy has good things to say on his blog[0]<p>> <i>"Brief digression. The code is written in Torch 7, which has recently become my favorite deep learning framework. I've only started working with Torch/LUA over the last few months and it hasn't been easy (I spent a good amount of time digging through the raw Torch code on Github and asking questions on their gitter to get things done), but once you get a hang of things it offers a lot of flexibility and speed. I've also worked with Caffe and Theano in the past and I believe Torch, while not perfect, gets its levels of abstraction and philosophy right better than others."</i><p>[0] - <a href="http://karpathy.github.io/2015/05/21/rnn-effectiveness/" rel="nofollow">http://karpathy.github.io/2015/05/21/rnn-effectiveness/</a>
I don't get it. I can't recall a single piece of learning content from Oxford that didn't have the audio quality of a tin can phone. I sounds like an over-compression issue, but it is just made even worse by horrible audio in what seems like tiny little boxes that lectures are held in. Someone please point Oxford towards a course on audio recording.
I took Nando's ML courses at UBC 2 years ago. He's great at explaining complex concepts in digestible chunks. He's able to show how ML theories are modeled after natural processes well too (such as how speech recognition and image processing work using deep learning and neural nets).