- 5 reviews
- 4 completed
[Edit] I upgraded this review from a 3 to a 4 star because the last set of lectures were so worthwhile. I think you can get a great deal of value from this class just by looking at the comprehensive overview in week 8 assuming you have some ml background already (e.g. you took Andrew Ng's course). Really great subject and I would love to give this class four stars except that it has had some technical snafus related to the speech rate and homework administration. If Dr. Shroff puts a little more time into this it should be a great introduction to learning from large quantities of data using modern machine learning methods.
I've you've taken Andrew Ng's machine learning course, this provides a great followup. Geoffrey Hinton takes us deep into neural networks, well past the back propagation algorithm that Andrew left off with. The content is more math intensive than ml class and the quizes are more rigorous, but not by too much. Assignments are done in octave (an open source Matlab clone). I've seen some complaints in the forums about questions and assignments being vague and underspecified. I don't feel that way very often, but I do think the learning curve will be steep if you haven't had a decent ml exposure already. The exciting part about this course is the content. Geoffrey is pushing us right to the brink of what's possible in terms of object and speech recognition. The deep neural networks that he is building too are really cutting edge. Over the last 4 years we've seen them make significant advances in many areas of machine learning. Geoffrey is a master of the field which means that he combines technical expertise with a deep knowledge of how these systems work. If you want to contribute to the future of advanced machine learning, this class is a great launching point.
This class was great, bettered only by andrew ng's ml class and cs212 from peter norvig. They got right into practical matters in nlp that helped me in kaggle's asap2 competition.
Peter taught me a new way to think about programming. His code is the most elegant I have ever read. Look at his 20 line implementation of a spelling corrector to get an idea of what real programming elegance can be. http://norvig.com/spell-correct.html Also the way that Peter broke down problems into relevant data structures and functions was simply beautiful. This class affects the way I code everyday.
Simply the best MOOC I have taken.