40719 Deep Learning

Course Description

The course helps to understand the fundamentals of Deep Learning. The course starts off gradually with multi-layer preceptrons and it progresses into the more complicated concepts such as attention and sequence-to-sequence models. This course also covers other models of deep learning such as convolutional neural networks, recurrent neural networks, deep generative models such as autoregressive, GAN, VAE, NFM, representation learning, and deep reinforcement learning methods. We use frameworks such as PyTorch and Tensorflow, which are very important for implementing deep Learning models.

Course Information

• Instructor: Hamid Beigy

• Teaching Assistants: Amir Moeini, Mohammad Moein Shirzady, Parsa Haghighi, Mehdi Dousti, Vida Ramezanian, Masoud Ghafouri, Ali Javani, Shima Rezaei, Zeinab Taghavi, Zahra Rahimi, Mehran Sarmadi, Reihaneh Zohrabi, Hamidreza Amirzadeh, Hamed Hematian, Amir Hossein Hadian, Ehsan Shobeiri, Hamed Saadati, Mojtaba Nafez, Zahra Khoramnejad, Elham Abolhasani, Ali Abdollahi, Mohammad Ebrahimzadeh, Alireza Heidari, Abolfazl Malekahmadi.

• Time and Location: Saturday/Monday: 10:30 am - 12:00 am, CE 201, virtual class

• Contact: Please contact the teaching staffs on Piazza site.

Required Texts

1. [GYC] Ian Goodfellow and Yoshua Bengio and Aaron Courville, Deep Learning, MIT Press, 2016.

2. [CH] Charniak, Eugene, Introduction to Deep Learning, The MIT Press, 2019.

3. [SB] Richard S. Sutton and Andrew G. Barto, Reinforcement Learning: An Introduction, Second edition. The MIT Press, 2018.

Grading Policy

1. 25%: Mid-term exam (1402/08/20).

2. 25%: Final exam (1402/10/25).

3. 30%: Homeworks.

4. 15%: Quiz.

5. 7.5%: Paper & Explore a theoretical or empirical question and present it. Deadline for choosing paper: 1402/08/20.

Lecture Schedule