- English
- فارسی
Deep Learning
Deep Learning
2nd Semester 401-402 (Jan. 2023)
Class Meetings: Sunday and Tuesday from 9:30am to 11:00am
Room #29-ECE Build.
Instructor: Dr. Mohammad Reza Ahmadzadeh
Office Location: ECE Building - 212B
Internal Telephone: Ext. 5370
External Telephone: Iran: +98 (0)31 33915370
Fax: Iran: +98 (0)31 33912451
Email: Ahmadzadeh @ iut.ac.ir
Homepage: https://ahmadzadeh.iut.ac.ir/
Office Hours:
I will try to be in my office on Sundays and Tuesdays from 11:00to 12:00 am, but I will always do my best to be available for students by appointment or any time that I am free.
Course Description:
This course covers the fundamentals of Deep Learning techniques.
Outline:
•Introduction
–Linear algebra review
–Probability and calculus chain rules
–Introduction to machine learning
•Multilayer Perceptrons
•Logistic regression and MLP
•Backpropagation
•Stochastic gradient descent
•Optimization
•Generalization
•Convolutional Networks
•Image Classification
•Recurrent Neural Nets
•Exploding and Vanishing Gradients
•ResNets and Attention
•Learning Probabilistic Models
•Mixture Modeling
•Boltzmann Machines
•Autoencoders
•Bayesian Hyperparameter Optimization
•Adversarial Learning
•Deep Reinforcement Learning
•Embedding learning
Textbook:
•I. Goodfellow, Y. Bengio, A. Courville, Deep Learning 2016.
Optional:
•Aurelien Geron, Hands-on Machine Learning with Scikit-Learn, Keras, and TensorFlow, 2019.
•François Chollet, Deep Learning with Python, 2021.
•Andrew W. Trask, Grokking Deep Learning, 2019.
•Daniel A. Roberts and Sho Yaida, Deep Learning Theory, 2021.
•C. M. Bishop, Neural Networks for Pattern Recognition, 1995.
•Michael Nielsen, Neural Networks and Deep Learning, 2017 (Online).
•K. L. Du, M. N. Swamy, Neural Networks and Statistical Learning, 2014.
•S. Haykin, Neural Networks and Learning Machines, 3rd Ed., 2009.
Lecture Notes:
Slides modified by Instructor and lecture notes can be obtained via E-Learning LMS (Enrolled students, Password protected).
Link: http://yekta.iut.ac.ir/
Prerequisites:
Probability and Stochastic Processes for Engineers or equivalent.
Grading Policy:
Midterm Exam ≈25%±5%
HW, Comp. Assignments and projects: ≈ 30%
Final exam ≈ 45%±5%
Time:
Sun. and Tue. from 09:30am to 11:00am
Files: