Xiaojin (Jerry) Zhu

Professor

University of Wisconsin-Madison

Courses

CS540 Introduction to Artificial Intelligence (fall 2023)

• Explore the fascinating world of artificial intelligence! This is the undergraduate AI course. Topics include mathematical foundation, game playing, deep learning, reinforcement learning.
• The Wisconsin AI100 Reaction Corpora (version 201609, version 201709, version 201809, version 202002)

CS639 Topics in Sequential Decision Making and Learning (last taught spring 2021)

• Theory and algorithms for active learning, multi-armed bandits, reinforcement learning, stochastic games.

CS760 Machine Learning (last taught fall 2019)

• Computational approaches to learning. What it means to learn. Algorithms for learning. Comparison and evaluation of learning algorithms. Students are strongly encouraged to have knowledge of probability, statistics, linear algebra, and calculus, and have good programming experience. (This course is intended for graduate students in other research areas that use machine learning. For machine learning students I suggest the course sequence 532->761->861)

CS761 Mathematical Foundations of Machine Learning (last taught spring 2017)

• Mathematical foundations of machine learning theory and algorithms. Probabilistic, algebraic, and geometric models and representations of data, mathematical analysis of state-of-the-art learning algorithms and optimization methods, and applications of machine learning. Students should have taken a course in statistics and a course in linear algebra. (Suggested course sequence for machine learning graduate students: 532->761->861)

CS769 Advanced Natural Language Processing (archived)

• This graduate course covers statistical methods for processing natural text. Some questions discussed in class: How does Google work? How many bits are there in each English word? Can your computer learn to laugh at a joke? Did Shakespeare write this book? Where did "The vodka is good, but the meat is rotten" come from?

CS/ECE 861 Theoretical Foundations of Machine Learning (last taught fall 2022)

• Advanced mathematical theory and methods of machine learning. Statistical learning theory, Vapnik-Chevronenkis Theory, model selection, high-dimensional models, nonparametric methods, probabilistic analysis, optimization, learning paradigms. (Suggested course sequence for machine learning graduate students: 532->761->861)

Talks

• Of Parrots and Monkeys: A Behind the Scenes Tour Through AI. Teaching Writing in the Age of ChatGPT Symposium. Madison, Wisconsin. July 25, 2023.
• From Breakthroughs to Empowerment: UW-Madison's AI Contributions and Accessibility. Exploring Artificial Intelligence @ UW-Madison: A summer 2023 webinar series. Madison, Wisconsin. July 14, 2023.
• Creative Bandit. Augmented Intelligence Workshop, Indiana University. September 8, 2022.
• Tragedy of the Data Scientists. MADLab 2022 Summer Workshop, University of Chicago. June 14, 2022.
• Game Redesign in No-regret Game Playing. Systems, Information, Learning and Optimization (SILO) Seminar, University of Wisconsin-Madison. Dec 1 2021.
• A Brief Introduction to Theoretical Foundations of Machine Learning and Machine Teaching. Simons Institute Workshop on Synthesis of Models and Systems. UC Berkeley. March 15 2021.
• Keynote: Introduction to Adversarial Machine Learning, ARFL and MADLAB Workshop on Adversarial Robustness of Machine Learning. Madison, WI. May 2020.
• Adversarial Machine Learning in Sequential Decision Making. The 1st Workshop on Adversarial Learning Methods for Machine Learning and Data Mining at KDD 2019. Anchorage, AK. August 2019.
• Toward adversarial learning as control at 2nd AOR/IARPA Workshop on Adversarial Machine Learning. University of Maryland, May 2018
• Machine Teaching and its Applications. Department of Computer Science, Duke University. 2018
• Machine Teaching as a Probe for Learning Mechanism in Humans at the Tsinghua Laboratory of Brain and Intelligence Workshop on Brain and Artificial Intelligence. Beijing, China. 2017
• Debugging the Machine Learning Pipeline at the Interpretable Machine Learning Symposium, NIPS 2017
• Introduction to Machine Teaching at the Workshop on Teaching Machines, Robots, and Humans, NIPS 2017
• Dagstuhl Seminar on Machine Learning and Formal Methods. August 2017, Germany. A Challenge in Machine Teaching.
• Simons Institute Workshop on Interactive Learning 2017, Berkely, CA. Machine Teaching in Interactive Learning
• ICML 2016 Workshop on Reliable Machine Learning in the Wild, New York. Machine Teaching and Security
• The Center for Information and Systems Engineering, Boston University. 2016.
• Department of Statistics, University of Indiana. 2016.
• Department of Computer Science and Engineering, University of Washington. Machine Teaching. 2016.
• College of Computer Science, Northeastern University. 2016.
• NIPS 2015 Workshop on Machine Learning from and for Adaptive User Technologies, Montreal, Canada. Machine Teaching for Personalized Education, Security, Interactive Machine Learning
• ICML 2015 Workshop on Machine Learning for Education, Lille, France. Machine Teaching. 2015.
• Systems Information Learning Optimization (SILO), University of Wisconsin-Madison. An Approach to Bridge Topology and Machine Learning, 2014.
• Signatures workshop. Topological Kernels, 2014.
• Simons Institute Workshop on Spectral Algorithms: From Theory to Practice. Some Applications in Human Behavior Modeling, 2014
• Keynote at ICML 2014 Workshop on Learning, Security and Privacy, Beijing China. Optimal Training Set Attacks on Machine Learning. 2014.
• Institute of Computer Science and Technology, Peking University. Corpus Attacks on Natural Language Processing and Machine Learning. 2014
• Department of Computer Science, Tsinghua University. Maximally Influencing Learning by Machine Teaching. 2014
• Department of Computer and Information Science, The University of Oregon. Machine Teaching: Frenemy of Machine Learning. 2014.
• School of Electrical Engineering and Computer Science Colloquium, Oregon State University. Machine Teaching: Frenemy of Machine Learning. 2014.
• Statistics colloquium, Department of Statistics, The University of Chicago. Machine Teaching: Frenemy of Machine Learning. 2014.
• Distinguished Speaker Series, Department of Computer Science, University of Virginia. How to Make Machines Learn: Passive, Active, and Teaching. 2014.
• Duke University Machine Learning Seminar Series. Machine Teaching: Frenemy of Machine Learning. 2014.
• Some Mathematical Models to Turn Social Media into Knowledge, Keynote at The Second Conference on Natural Language Processing & Chinese Computing, Chongqing, China 2013
• How can a Machine Learn: Passive, Active, and Teaching, Chongqing University, China 2013
• Three Assertions about Interactive Machine Learning, Microsoft Research Faculty Summit, 2013
• Beyond Label Propagation, ICML 2013 Classic Paper Prize talk, 2013
• Capacity, Learning, Teaching, NSF Workshop on Integrating Approaches to Computational Cognition, 2013
• Can Machine Learning Rationalize Simple Human Teaching Behaviors?, UCSD Optimal Teaching Workshop, 2012
• Machine Learning Theory by the People, for the People, of the People, Machine Learning and Applications Seminar, Purdue, 2011
• Adding Domain Knowledge to Latent Topic Models, University of Massachusetts Amherst, 2011
• Is Machine Learning the Wrong Name?, Boston University, 2010
• Computers Discover Wishes and Creativity in Text, Indiana University-Purdue University Indianapolis, 2009
• HAMLET, IBM, 2009
• Semi-Supervised Learning by Multi-Manifold Separation, IMA Minnesota, 2008
• Text-to-Picture Synthesis, Carnegie Mellon University, 2008
• Online Semi-Supervised Learning, 40th Symposium on the Interface: Computing Science and Statistics, 2008
• Semi-Supervised Learning in Computers and Humans, University of Michigan--Ann Arbor, 2007
• Semi-Supervised Learning: an overview, Joint Statistical Meetings, Seattle, Washington, 2006

Tutorials

• Tutorial on Adversarial Sequential Decision Making at IJCAI 2022, Vienna, Austria.
• Tutorial on Statistical Machine Learning for NLP at CCF ADL 46 in Chongqing, China, 2013.
• Tutorial on Understanding Social Media with Machine Learning at CCF ADL 39 in Beijing, China, 2013.
• Tutorial on Graphical Models at KDD 2012.
• Tutorial on All of Graphical Models at The tenth International Conference on Machine Learning and Applications (ICMLA11), 2011.
• Tutorial on Semi-Supervised Learning at University of Chicago Machine Learning Summer School 2009
• Tutorial on Semi-Supervised Learning for Natural Language Processing at ACL 2008 with John Blitzer
• Tutorial on Semi-Supervised Learning at ICML 2007
• Tutorial and practice session on Semi-Supervised Classification: learning from labeled and unlabeled data at AERFAI Summer School. Granada, 2006

Local interest

• Machine Learning @ University of Wisconsin-Madison
• How University of Wisconsin-Madison Computer Science Graduate Program Works, Approximately
• Future CS timetables.
• HAMLET (Human, Animal, and Machine Learning: Experiment and Theory). Old archive
• Fall 2011 Meet the AI Group (organized by Bryan Gibson).
• Spring 2011 Structured Sparsity Reading Group (organized by Junming Xu).
• Fall 2010 Non-i.i.d. Learning Reading Group (organized by Kwang-Sung Jun).
• Spring 2010 Learning Math for Machine Learning (LMML) Reading Group (organized by David Andrzejewski)
• Fall 2009 Bayesian Nonparametrics Reading Group (organized by Andrew Goldberg)

Random stuff

• Excellent, free museums within walking distance on campus:
  • Geology Museum: fossils & minerals
  • Chazen Museum of Art: paintings & sculpture
  • L.R. Ingersoll Physics Museum: hands-on physics
  And when you need it:
  • Spiked Math
  • PhD Comics
  • Philosophical humor
  • xkcd
  • the ONION
  • s---myreviewerssay
• Not sure how to pronounce Chinese names like Zhu, Cai, Qin, Xu? Learn it in five minutes
• Build a spectroscope from a CD and a cereal box
• Aurora Borealis! How to See the Northern Lights from Wisconsin and Elsewhere
• How to observe the flash spectrum during total solar eclipse