The following is a schedule of the lectures and presentations for CS 5043 Advanced Machine Learning for Spring 2008. This schedule will be updated throughout the semester. All readings are from Pattern Recognition and Machine Learning by Christopher Bishop unless otherwise noted.
| Date | Topic | Assigned Reading | Assigned | Due |
| Jan 15 (Week 1: Intro and Class Design) | Introduction/Class design/Undirected Graphical Models | 8.3 | ||
| Jan 17 | Finalized course design/Undirected graphical models | |||
| Jan 22 (Week 2: Advanced graphical models) | Hidden Markov Models | 13.1-13.2 | ||
| Jan 24 : | Abstract Hidden Markov Models | Paper | Summary 1 | |
| Jan 29 (Week 3: Advanced graphical models) | Dynamic Bayesian Models | Summary 2 | ||
| Jan 31 | Exact and approximate inference | 8.4.3, 8.4.4 | ||
| Feb 5 (Week 4: Advanced graphical models) | Non-parametric density estimation | Thrun's Ch 4 (on D2L) | Summary 3 | |
| Feb 7 | Using graphical models for robot localization | |||
| Feb 12 (Week 5: Advanced Graphical models) | Particle filtering for robots : real-world particle filtering | Thrun's Ch 5 (on D2L | ||
| Feb 14 | Relational learning: Relational Probability Trees | Neville's paper | Summary 4 | |
| Feb 19 (Week 6: Advanced Graphical Models) | Relational learning: Spatiotemporal Relational Probability Trees | Paper on D2L | ||
| Feb 21 | Relational learning: Relational Dependency Networks | Neville's paper | Summary 5 | |
| Feb 26 (Week 7: Advanced Graphical Models) | MCMC and Gibbs Sampling and RDNs | Optional paper on MCMC on D2L | ||
| Feb 28 | Project 1 presentations | |||
| Mar 4 (Week 8: Kernel Methods) | Introduction to kernel methods | Chapter 6: 6-6.2 | ||
| Mar 6 | Kernels | 6.3 | Project 2 | Summary 6 (due on all of Chapter 6) |
| Mar 11 (Week 9: Kernel Methods) | Radial Basis Functions, Project proposals, Support Vector Machines | Chapter 7.1 | Project 2 proposals | |
| Mar 13 | Support vector regression | Chapter 7.1 continued | Summary 7 | |
| Mar 15-23 | Spring Break! |
|||
| Mar 25 (Week 10: Kernel Methods) | Support Vector regression | Bishop 7.1 | Project 2 status | |
| Mar 28 | Least Squares SVM and SVRs | Suykens paper on D2L | ||
| Apr 1 (Week 11: Advanced Reinforcement Learning) | Hierarchy: Options | Precup's paper on D2L | Project 3 | Summary 8 |
| Apr 3 | Project 2 presentations | Project 2 | ||
| Apr 8 (Week 12: Advanced Reinforcement Learning) | Project 2 presentations, Project 3 proposals | Dietterich's paper on D2L | Summary 9, Project 3 proposals | |
| Apr 10 | Hierarchy: Max-Q | |||
| Apr 15 (Week 13: Advanced Reinforcement Learning) | Learning abstractions and hierarchy automatically | Hengst and McGovern papers on D2L | Summary 10 | |
| Apr 17 | Learning other forms of abstraction: Proto-RL | Paper | Summary 11 | |
| Apr 22 (Week 14: Advanced Reinforcement Learning) | Proto RL | Project 3 status | ||
| Apr 24 | Practical function approximation | Ng paper on D2L | ||
| Apr 29 (Week 15: Course wrapup) | Intrinsic motivation | Simsek paper on D2L | Summary 12 | |
| May 1 | Transfer learning | Konidaris paper on D2L | Summary 13 | |
| May 7 | Final exam 4:30-6:30: Project 3 presentations |
|||