CS 519-006 Deep Learning
School of Electrical Engineering and Computer Science
Oregon State University
Corvallis, OR 97331
Instructor: Fuxin Li (KEC 2077)
Class Time: TR 4-5:20pm, Location: KEC 1001
TA: Mingbo Ma
TA: Mingbo Ma, 3-5PM Wednesday, KEC 4130
Fuxin Li: 4-6PM Monday, KEC 2077.
We use Canvas
for discussions and grades.
For technical questions (e.g., HW), first check if the same question has been asked on Canvas;
if not, ask it there (we monitor the discussions).
You will be rewarded for answering questions on Canvas.
For non-technical questions (e.g., grading), .
In a Nutshell
An introduction to the concepts and algorithms in deep learning; basic feedforward neural networks,
convolutional neural networks, recurrent neural networks, deep belief nets, autoencoders and deep
networks in reinforcement learning.
Prerequisites: CS 534 Machine Learning or equivalent knowledge recommended.
Recommended textbook (recommended; this course is self-contained):
- Deep Learning
by Ian Goodfellow, Yoshua Bengio and Aaron Courville
This is an unfinished book yet very close to finishing. Most of the contents are available and it seems to be the only dedicated deep learning textbook that I know of right now.
Learning Objectives of the Course:
- Have a solid understanding in the concepts of deep learning
- Gain some intuitions on deep networks, understand why do they perform well in practice
- Understand the training of deep learning models and able to explain and toggle parameters
- Be able to use at least one deep learning toolbox to design and train a deep network
- Be able to design new deep learning algorithms and architectures.
- Initial quiz 5% (Based on participation)
- 3 Biweekly Quizzes (5%x3=15%)
- 4 Assignments (30%)
- Final Project (50%) -- in groups of three, including initial proposal (10%) and final presentation (40%)
Programming assignments can be performed in MATLAB or Python. At least one assignment would be a written assignment about the essential mathematical foundations.
A self-designed project on deep learning on your specific data source. Some default project topics will be provided.
NO FINAL EXAM.
Please note that all homework (except the final project) should
be your own work. Any collaboration that requires written
communication is forbidden. You should also not copy
answers from books or internet resources.
You are encouraged to study together and discuss general strategies for
solving problems but not at the level of written solutions.
Please read the
department's academic dishonesty policy for more details.
You should not use any web sources for answering the homework
questions unless explicitly instructed to do so.