Advanced Predictive Models and Applications for Business Analytics
Informal name: Deep Learning, Graphical Models and Reinforcement Learning
All announcements will be made on the Forum
The goal of this class is to cover a subset of advanced machine learning techniques, after students have seen the basics of data mining (such as in in IDS 572) and machine learning (such as in IDS 575). Broadly, we will cover topics spanning graphical models, deep learning and reinforcement learning. Graphical models are useful for inferring outcomes and making predictions conditional on preceding/related events, even when we do not have full information. They have found success in tracking, speech recognition, language modeling (Hidden Markov Models), image segmentation (Markov Random Fields) and other applications. Similarly, we will study popular deep learning architectures, their design choices and how they are trained. We will also study recurrent and convolutional architectures which achieve state of the art in challenging prediction tasks in text and computer vision applications. Finally, we will look at online and reinforcement learning problems and their role in sequential decision making problem areas such as transportation and retail.
- Semester: Fall 2019
- Lecture times: Thursdays 6.30 PM to 9.00 PM at DH 210 (location subject to change)
- Optional Recitations: TBD
- Online communication: Forum (sign up needed!)
- Offline communication:
- Instructor Office Hours: 2.00 to 3.00 PM at UH 2404
- TA Office Hours: TBD
Textbook and Materials
08/29 : Motivating Applications, Machine Learning Pipeline (Data, Models, Loss, Optimization), Backpropagation
09/05 : Feedforward Networks: Nonlinearities, Convolutional Neural Networks: Convolution, Pooling
09/12 : Jumpstarting Convolutional Neural Networks: Visualization, Transfer, Practical Models (VGG, AlexNet)
09/19 : Text and Embeddings: Introduction to NLP, Word Embeddings, Word2Vec
09/26 : Recurrent Neural Networks: Sequence to Sequence Learning, RNNs and LSTMs
10/03 : Unsupervised Deep Learning: Generative Adversarial Networks, Variational Autoencoders
10/17 : Canceled
10/24 : Online Learning: A/B Testing, Multi-armed Bandits, Contextual Bandits
10/31 : Reinforcement Learning: Policies, State-Action Value Functions, Q-Learning
11/07 : Deep Reinforcement Learning: Function Approximation, DQN for Atari Games, AlphaGo Zero
11/14 : Graphical Models: How they complement Deep Learning
11/21 : Inference in Graphical Models: Belief Propagation, Markov Chain Monte Carlo
12/05 : Learning Graphical Models: Maximum Likelihood Estimation, EM Algorithm
- 09/05: Assignment 1. Due 09/18
- 09/19: Assignment 2. Due 10/02
- 10/03: Assignment 3. Due 10/16
- 10/24: Assignment 4. Due 11/06
These involve reimplementing recent deep-learning techniques and understanding their behavior on interesting datasets. Always mention any sources that were relied on, in your assignment solutions. Submission deadline is BEFORE 11.59 PM on the concerned day. Late submissions will have an automatic 20% penalty per day without exceptions. Use Blackboard for uploads.
There is a group project component to this course. Additional details will be provided very soon.
- 10/10 : Exam I (same venue as lectures, and during class hours)
- 12/12 : Exam II (finals week, subject to change)
These are closed book, but one 8.5x11-inch handwritten cheatsheet is allowed. No computers and communication devices are allowed.
- Assignments: 8% + 8% + 8% + 8%
- Project: 20%
- Exams: 20% (Exam I) + 20% (Exam II)
- Participation: 8% (online and offline)
- This is a 4 credit graduate level course offered by the Information and Decision Sciences department at UIC.
- Please see the academic calendar for the semester timeline.
- Students who wish to observe their religious holidays (https://oae.uic.edu/religious-calendar/) should notify the instructor within one week of the first lecture date.
- Please contact the instructor at the earliest, if you require accommodations for access to and/or participation in this course.
- Please refer to the academic integrity guidelines set by the university.