CS598: Machine Learning in Computational Biology


Instructor: Jian Peng
Assistant Professor
Department of Computer Science
University of Illinois at Urbana-Champaign
2118 Siebel Center
201 N Goodwin Ave Urbana, IL, 61801
Email: jianpeng AT illinois.edu

Teaching Assistant: Rongda Zhu (rzhu4@illinois.edu)

Location: 4101 Materials Science & Eng Bld

Time: 02:00PM - 03:15PM, Tuesday/Thursday

Office hours: 03:15PM - 04:45PM, Thursday

Course Information

This course focuses on modern machine learning techniques in computational biology, including probabilistic modeling, feature selection, graphical models, approximate inference and learning, Monte Carlo methods and neural networks. Students will learn the development of the theoretical concepts for these methods and the applications of these methods to a variety of problems in computational biology. This course is appropriate for graduate students in computer science, bioengineering, mathematics and statistics. Familiarity with basic statistics, probability and algorithms is expected.

Introductory materials

Machine Learning: Pattern Recognition and Machine Learning by Christopher Bishop, Cambridge University Press, 2007
This leading textbook provides a comprehensive introduction to the fields of pattern recognition and machine learning. It is aimed at advanced undergraduates or first-year PhD students, as well as researchers and practitioners.

Biology: Molecular Biology for Computer Scientists by Larry Hunter. Downloadable PDF here.
You can learn more from online videolectures at http://ocw.mit.edu/courses/biology/7-012-introduction-to-biology-fall-2004/video-lectures/

Course project

Schedule

Date Presenter Lecture/Paper
08/25/2015 Jian Peng Introduction to this course [slides]
08/27/2015 Jian Peng Sequence data: part 1 [slides]
Papers for variational inference:
Neural Variational Inference and Learning in Belief Networks
Stochastic Variational Inference
09/01/2015 Jian Peng Sequence data: part 2 [slides]
Logistic regression and maximum entropy models.
Introduction to Conditional Random Fields
09/03/2015 Jian Peng Matrix data: part 1 [slides]
A Neural algorithm of artistic style
Sequence-to-sequence learning with neural networks
Deep learning for protein structure prediction
Conditional Neural Fields
09/08/2015 Jian Peng Matrix data: part 2 [slides]
Sparse regression
Subgradient
SVD in Netflix challenge
Restricted Boltzmann Machines for Collaborative Filtering
09/10/2015 Jian Peng Network data [slides]