一、課程說明 (Course Description)
This class introduces the concepts and techniques of deep learning. The course consists of
three parts. In the first part, we give a quick introduction of classical machine learning and
review some key concepts required to understand deep learning. In the second part, we
discuss how deep learning differs from classical machine learning and explain why it is
effective in dealing with complex problems such as the image and natural language
processing.
Various CNN and RNN models will be covered. In the third part, we introduce the deep
reinforcement learning and its applications.

This course also gives coding labs. We will use Python 3 as the main programming language
throughout the course. Some machine learning libraries such as Scikit-learn and Tensorflow
will be explained and heavily used.

Students are required to have proper understanding of Calculus, Linear Algebra, Probability
Theory, and the Python programming language. Although it would be helpful, knowledge
about classical machine learning is NOT required.

IMPORTANT: Students will group (3~4 people a group). This class requires **each group of
students to prepare a GPU card** to perform the necessary computing. You can follow this
link
(http://timdettmers.com/2017/04/09/which-gpu-for-deep-learning/) to decide which GPU card
to go for. NO GPU CARD PROVIDED IN THE CLASS.

二、指定用書 (Textbook)
Ian Goodfellow, Yoshua Bengio, Aaron Courville, Deep Learning, MIT Press, 2016, ISBN:
0387848576

四、教學方式 (Teaching Method)
Video Lecture + Labs

五、教學進度 (Syllabus)
1. Fundamentals of Machine learning (5 weeks)
2. Neural Networks (NNs): Design
3. NN Optimization and Regularization
4. CNNs
5. RNNs
6. Unsupervised learning
7. Semi-supervised & transfer learning
8. Deep reinforcement learning (2 weeks)

六、成績考核 (Evaluation)
Midterm exam/project: 20%
Assignments: 60%
Final exam/project: 20%