This graduate level research class focuses on deep learning techniques for vision, speech and
natural language processing problems.
It gives an overview of the various deep learning models and techniques, and surveys recent advances in the related fields.
Four homeworks and one final project with a heavy programming workload are expected.
This course uses Tensorflow as the primary programminging tool. However, other toolkits including pyTorch, or MxNet are also welcome.
All the programming problems in the homework should be done with IPython Notebook.
Both code and experimenal results are required.
Google cloud will be used as the main programming platform. Students are also encouraged to install their computer with GPU cards.
20% paper presentation and course attendence
40% final project
Homework should be uploaded on Coursework.
Upload ipython-notebook instead of python file.
There is no required book for this class. But the following reading materials are recommended to read beyond the class:
Ian Goodfellow and Yoshua Bengio and Aaron Courville: Deep Learning