Hello, dear friend, you can consult us at any time if you have any questions, add WeChat: THEend8_
Course Description:
Deep learning is either a pattern classification or feature representation learning technique that has multiple levels of non-linear operations. This course will cover algorithms in Deep Learning, such as convolutional neural networks, recursive neural networks, generative adversarial nets, and deep reinforcement learning … , as well as application areas, such as vision and NLP.
Course Evaluation:
Determination of grade and performance consists of two parts: one midterm (20%) and one final exam (20%) and homework (60%). The project oral presentation may be held at the end of the semester.
Grading:
Curved to A, B, C, D
Prerequisites:
• Familiarity with basic computer science principles and skills.
• Knowing to code in Python and Pytorch.
• Familiarity with basic mathematics and statistics, like probability theory, basic linear algebra.
Reference books:
Simon J. D. Prince. “Understanding Deep Learning” . ISBN: 9780262048644
Project Policy:
• The homework should be done individually.
• Any form. of cheating (including copying or reusing code from any source) will result in a 0 (zero) point for the project.
• Students must submit their homework deliverables at the specified due dates. Late submission will not be accepted unless being approved by the instructor.
Tentative Topical Outline:
• Neural Networks
• Hopfield Network
• Boltzmann Machine
• Deep Neural Network
• Convolutional Neural Network
• Recurrent Neural network
• Encoder and decoder
• Attention Mechanism
• Deep Auto-encoder
• VAE
• Autoregressive
• Generative Adversarial Networks
• WGAN and EBGAN
• Conditional GAN
• SeqGan
• Deep Reinforcement Learning
• Transfer Learning
• Explainable Learning
Other Policies:
• Tests.
A student absent from a test will receive a grade of 0 for that test. Usually, there will be no make-up test provided. Exams are to be done individually. Inappropriate contact during an exam will be considered cheating and will be processed as such via university judiciary channels!
• Class attendance.
A student absent from class is responsible for all assigned work, tests, or material covered during the class. Attendance may be taken daily. Missing class will lead to final grade deduction. Students who miss the class without a reason will lead to grade deduction from the final grade. The final grade will be deducted 1 point for the first miss, 2 points for the second miss, 3 points for the third miss, and so on.
• Cheating.
Unless otherwise stated explicitly in an assignment or lab, each student must do his or her work independently. Publicly-available sources for code or other material may be freely used if appropriately attributed. Each student is responsible for protecting his or her files from access by others. Work that is essentially the same and submitted without proper attribution is considered to be a violation of academic dishonesty policies by all those submitting the work, regardless of who did the work. Any duplication of a homework assignment will lead to the application of the University and Departmental policies on academic dishonesty.