STAT4402/STAT7503 Advanced Statistics II

Deep Learning

Semester 2 2019

Lecturer: Nan Ye
Lecture Time & Location: Mon 11a-12pm @ 08-212, Wed 9-10am @ 14-116, Thu 1-2pm @ 83-C415
Tutorial Time & Location: Fri 12pm-1pm @ 47A-241

Deep learning, a major sub-field of machine learning, has recently been applied to solve many real world problems. This course gives the students the basic ideas and intuition behind deep learning. Students taking this course will understand how, why and when the algorithms work, and be able to effectively apply deep learning methods to practical problems. This course begins with basics of machine learning, followed by a broad coverage on deep neural networks, including some major deep neural network architectures, optimization of network parameters, and applications in classification, regression and reinforcement learning. Python will be used for this course.

This course is for advanced undergraduate and graduate students.


Event Date Description Materials
Week 1
Lecture 1 22 Jul 2019 Introduction slides
Lecture 2 24 Jul 2019 Regression slides
Lecture 3 25 Jul 2019 Classification slides
Tutorial 1 questions
Week 2
Assignment 1 out 2019
Lecture 4 29 Jul 2019 Principal Component Analysis slides
Lecture 5 31 Jul 2019 Statistical Learning Theory slides
Lecture 6 1 Aug 2019 Model Selection slides
Tutorial 2 2 Aug 2019 questions
Week 3
Lecture 7 5 Aug 2019 Perceptrons slides
Lecture 8 7 Aug 2019 Adaline slides
Lecture 9 8 Aug 2019 Hopfield Networks slides
9 Aug 2019 programming crash course
Week 4
Assignment 1 due 12 Aug 2019 submit on Blackboard by 11am
Assignment 2 out 12 Aug 2019
Lecture 10 12 Aug 2019 Gradient-based Learning slides
Lecture 11 15 Aug 2019 Multilayer Perceptron slides
Tutorial 3 16 Aug 2019 questions
Week 5
Lecture 12 19 Aug 2019 Deep Learning Software slides
Tutorial paper out 19 Aug 2019 task sheet released
Lecture 13 21 Aug 2019 Deep Learning Software (cont.) slides
Lecture 14 22 Aug 2019 Convolutional Neural Nets slides
Tutorial 4 23 Aug 2019 questions
Week 6
Assignment 2 due 26 Aug 2019 submit on Blackboard by 11am
Lecture 15 26 Aug 2019 Convolutional Neural Nets (cont.) slides
Lecture 16 28 Aug 2019 Convolutional Neural Nets (cont.) slides
Lecture 17 29 Aug 2019 Recurrent Neural Nets slides
Tutorial 5 30 Aug 2019 questions
Week 7
Assignment 3 out 2 Sep 2019
Project proposal due 2 Sep 2019 submit on Blackboard by 5pm
Lecture 18 2 Sep 2019 Recurrent Neural Nets (cont.) slides
Lecture 19 4 Sep 2019 Recurrent Neural Nets (cont.) slides
Lecture 20 5 Sep 2019 Numerical Optimization slides
Tutorial 6 6 Sep 2019 questions
Week 8
Lecture 21 9 Sep 2019 Numerical Optimization (cont.) slides
Lecture 22 11 Sep 2019 Initialization and Input Transformation slides
Batch Normalization slides
Lecture 23 12 Sep 2019 Adaptive Learning Rates slides
Tutorial 7 13 Sep 2019 questions
Week 9
Lecture 24 16 Sep 2019 Improving Generalization slides
Lecture 25 18 Sep 2019 Adversarial Learning slides
Assignment 3 due 2 Sep 2019 submit on Blackboard by 5pm
Lecture 26 19 Sep 2019 Activation functions slides
Tutorial 8 20 Sep 2019 questions
Week 10
Lecture 27 23 Sep 2019 Residual Networks slides
Lecture 28 25 Sep 2019 Attention slides
Lecture 29 26 Sep 2019 Autoencoders slides
Tutorial 9 27 Sep 2019 questions
Tutorial paper due 1 Oct 2019 submit on Blackboard by 5pm
Week 11
Lecture 30 9 Oct 2019 Variational Autoencoders slides
Lecture 31 10 Oct 2019 Generative Adversarial Networks slides
Tutorial 10 21 Oct 2019 questions
Week 12
Lecture 32 14 Oc 2019 Reinforcement Learning slides
Lecture 33 16 Oct 2019 Reinforcement Learning (cont.) slides
Lecture 34 17 Oct 2019 Review slides
Tutorial 11 18 Oct 2019 questions
Week 13
Project seminars 21 Oct 2019
Project seminars 23 Oct 2019
Project seminars 24 Oct 2019
Project report due 31 Oct 2019 submit on Blackbord by 5pm
Reflective essay due 2 Nov 2019 submit on Blackboard by 5pm