Schedule


Week# Date Title HW MP Grad Project
1 Aug 22 Lecture 1: Course outline and Overview of Mini Projects:
  1. Autonomous Vehicle (AV) Safety Analytics
  2. Healthcare analytics
  3. Security
Overview of key data analytics and ML concepts.
Aug 24 Lecture 2: Probability Basics Overview, P-values, Hypothesis Testing, Fitting Distributions (KS test, KL divergence) HW0 release
2 Aug 29 Lecture 3: Mini-project 1 descriptions and task specifications; In-class Activity 1 (Probability concepts, hypothesis testing, jupyter notebook) MP1 release
Aug 31 Lecture 4: Overview of unsupervised clustering algorithms: K means, EM, and GMM among others.
3 Sep 5 No classes – Labor Day
Sep 7 Lecture 5: Overview of regression and feature transformation techniques (PCA, Factor analysis, and distance metrics)
4 Sep 12 Lecture 6: Real world examples of feature transformation HW0 due, HW1 release
Sep 14 Lecture 7: In class activity on feature transformation
Feb 16 Discussion 1: session on unsupervised techniques (optional) MP1 checkpoint
5 Sep 19 Lecture 8: Introduction to Probabilistic Graph Models (PGMs) and applications; Naïve Bayes, conditional independence
Sep 21 Lecture 9: Bayesian Networks
Sep 23 Discussion 2: session on feature transformation (optional) MP1 final checkpoint due
6 Sep 26 Discussion section on Bayesian Network Proposal due
Sep 28 Lecture 10: Bayesian networks continue, In-class Activity 2 on Bayesian Networks
7 Oct 3 Lecture 11: Mini-project 2: Application of Bayesian Networks/PGMs to Health-care Domain; Guest Lecture MP2 release
Oct 5 Lecture 12: Markov models: Data driven methods for building Markov Models for large-scale computer system (NCSA’s Blue Waters) addressing performance and reliability; real example with data
Oct 7 Discussion 3: session on Bayesian Networks (optional)
8 Oct 10 Lecture 13: Hidden Markov Models (HMM)
Oct 12 Lecture 14: In-class Activity for Midterm revision MP2 checkpoint
9 Oct 17 Lecture 15: Midterm
Oct 19 Lecture 16: HMM continued
Oct 21 Checkpoint 1
10 Oct 24 Lecture 17: Application of Bayesian Networks and HMMs to secure systems; Guest Lecture MP2 Task 1.1.d–1.1.f Supplement Materials
Oct 26 Lecture 12: In-class Activity 5 on HMM
Oct 28 Discussion 4: session on Midterm exam solutions (optional)
11 Oct 31 Lecture 19: Factor Graphs, introduction to Mini-project 3 MP2 final checkpoint due MP3 release
Nov 2 Lecture 20: Factor Graphs Continued
Nov 4 Checkpoint 2
12 Nov 7 Lecture 21: Belief Propagation and approximate methods (MCMC and Gibbs sampling)
Nov 9 Lecture 22: In-class Activity 6 on Factor Graphs
Nov 11 MP3 checkpoint 1
13 Nov 14 Lecture 23: Sampling-based Methods and SVMs
Nov 16 Lecture 24: Neural networks MP3 checkpoint 1
14 Nov 21 No classes – Fall break
Nov 23 No classes – Fall break
15 Nov 28 Lecture 25: Reinforcement Learning and solution techniques via Partially Observable Markov Decision Processes
Nov 30 Lecture 26: Real world Cloud Datacenter-based example of combining RL with PGMs
Dec 2 Discussion 5: session on data and problem solving (optional)
16 Dec 5 Lecture 27: Grad Project Presentation MP3 submission
Dec 7 Lecture 28: Bayesian Deep Learning to address model and data uncertainties Final submission
Dec 8 No classes – Reading Day
TBD Final Exam