Course Review: Neural Networks for Machine Learning, University of Montreal
A few weeks ago I completed the 16 week “Neural Networks for Machine Learning” on-line course from University of Montreal to deepen my understanding of Artificial Neural Networks and their fascinating properties. The course is taught by Professor, Geoffrey Hinton, which is one of the grand old men in the field with numerous contributions such as back propagation and Boltzmann machines.
The course is well laid out and gets around a lot of the basic properties and developments within the field, and there were many “gold nuggets” in the material. It is a few years(?) old, so the newest developments are not included, but it excellently introduces the foundation and the general properties. It thus lays a solid foundation for working productively with modern frameworks such as Keras, Theano and Google’s Tensorflow, although the coding exercises included in the course were done with GNU Octave. On the downside: In my opinion there were gap between the level of the video lectures and the level of the calculations necessary to complete the quizzes. Having a smooth learning curve is especially important for online courses where there is not as great possibilities to ask questions and discuss the material as in regular courses.
Anyway, I can highly recommend the course for anyone with a bit of machine learning experience, who want to work with Neural Networks. For a more general introductory course, I can recommend Andrew Ng’s Machine Learning Course, which gives a more general introduction to machine learning in general as well as an introduction to multiple machine learning algorithms.
Esben Jannik Bjerrum