Time: Tuesday, Thursday
11:00pam-12:15pm
Location: Sennott Square, Room 5313
Instructor: Milos
Hauskrecht
Computer Science Department
5329 Sennott Square
phone: x4-8845
e-mail: milos_at_cs_pitt_edu
office hours: by appointment
Course description
Lectures
TBA
Paper presentations
Projects
The goal of the field of machine learning is to build computer systems that learn from experience and that are capable to adapt to their environments. Learning techniques and methods developed by researchers in this field have been successfully applied to a variety of learning tasks in a broad range of areas, including, for example, text classification, gene discovery, financial forecasting, credit card fraud detection, collaborative filtering, design of adaptive web agents and others.
The objective of the Advances Machine Learning course is to expand on the material covered in the introductory Machine Learning course (CS2750). It focuses on special topics in ML such as exact and approximate inference in graphical models, dimensionality reduction and component analysis methods, latent variable models, models of documents and words, time series models and selected topic from deep neural networks. The course will consist of (student-lead) presentations and discussions. Students will be evaluated based on their participation in discussions, presentations and projects.
Prerequisites
CS 2750 Machine Learning, or the permission of the instructor.
In the first part of the course we will use readings from:
In addition we will use conference and journal paper readings that will be distributed electronically or in a hardcopy form.
Lectures | Topic(s) | |
---|---|---|
August 28 | Course Administration Readings: | |
August 30 | Graphical models: Bayesian belief networks, MRFs, conversions Readings:
| |
September 4 | Graphical models: inference on chains and factor graphs Readings:
| |
September 6 | Graphical models: inference on clique trees Readings:
| |
September 11 | Monte Carlo methods: sampling BBNs, rejection sampling, importance sampling
Readings:
| |
September 13 | Monte Carlo methods: MCMC Variational methods Readings:
| |
September 18 ( | PCA, Autoencoders (presenter Xiaozhong Zhang)
Readings: | |
September 20 | Latent variable models (presenter Cui Tianyi)
Readings:
| |
September 25 | Non-linear dimensionality reduction and kernels: eigenmaps, isomaps, locally linear embeddings (presenter: Hanzhong Zheng)
Readings:
| |
September 27 | Singular value decomposition, applications of SVD, non-negative matrix factorization (presenter: Sumendha Singla)
Readings:
| |
October 2 | Document and topic models: pLSA, LDA (presenters: Andrew Levandoski and Jonathan Lobo)
Readings:
| |
October 4 | Word similarity and word models: word2vec, CBOW, graph-based similarities (presenter: Ahmed Magooda)
Readings:
| |
October 9 | Gaussian Processes: basics, regression (presenter: Zhenjiang Fan)
Readings:
| |
October 11 | Gaussian Processes: classification (presenter: Jinpeng Zhou)
Readings:
| |
October 18 | Sequences and Time series: Markov models, Dynamic Belief networks, Hidden Markov models (presenter: Yanbing Xue)
Readings:
| |
October 23 | Time Series: Autoregressive models (first and k-order AR, ARMA, ARIMA)(presenter: Mingda Zhang)
Readings:
| |
October 25 | Sequences and Time series: Linear dynamical model (presenter: Matt Barren)
Readings:
| |
October 30, 2018 | Sequences and Time series: Particle filters (presenter: Ekaterina Dimitrova)
Readings:
| |
November 1, 2018 | Sequences and Time series: Continuous-time models (presenter: Siqi Liu)
Readings:
| |
November 6, 2018 | Project presentations
Readings:
| |
November 8, 2018 | Sequences/Deep Neural Nets: Recurrent neural networks, Long-short term memory (LSTM) (presenter: Jeongmin Lee)
Readings: | |
November 13, 2018 | Sequences/Deep Neural Nets: Convolutional neural networks (presenter: Yu Ke)
Readings: | |
November 15, 2018 | Deep Neural Nets: Deep generative models (presenter: Hung Chau)
Readings: | |
November 20, 2018 | Deep Neural Nets: Generative Adversarial Networks (presenter: Thaker Kuushboo)
Readings: | |
November 27, 2018 | Deep Neural Nets: Applications (presenters: Xiaoyu Ge, Longhao Li)
Readings: |
Course webpage for CS2750, the introductory Machine Learning course from Spring 2018. It is the prerequisite of CS3750.
Readings will be assigned before the class at which the discussion on the topic takes place. Most of the readings will be electronic, however, some readings will be in the paper form or from the books. The students should always read the book chapter and paper assigned and be prepared for the class. Short randomly-scheduled quizes can be administered to recheck if students follow the readings.
See the list of readings for different topics (currently incomplete)
Every student is expected to be in charge of at least one topic, present it,
and lead the discussion on the topic during the class.
The readings for each topic will be distributed electronically. The assignment of the papers will be discussed during the first two weeks of the course.
There are two projects for course. The first project (a group project) will be assigned and due in the middle of the semester. The final project (due at the end of the semester) and is more flexible: a student can choose from a set of topics/problems or propose his/her own topic to investigate. If you plan to propose your own project/topic you will need to submit a short (one page) proposal for the purpose of approval and feedback. In general, the final project must have a distinctive and non-trivial learning or adaptive component.