LCI

With Kevin Leyton Brown in the lead, this group has made significant contributions to algorithmic game theory, multiagent systems and mechanism design. David Poole also contributes to this group with his work on decision processes and planning. The research problems attacked by this group are therefore of great importance to e-commerce, auctions and advertising.

To learn more, please see:

• Kevin Leyton-Brown's research page
• Kevin Leyton-Brown's publications
• David Poole's research page
• David Poole's publications
• The book Multiagent Systems: Algorithmic, Game-Theoretic, and Logical Foundations, by Yoav Shoham and Kevin Leyton-Brown
• The book Essentials of Game Theory: a Concise, Multidisciplinary Introduction, by Kevin Leyton-Brown and Yoav Shoham
• The book Artificial Intelligence: Foundations of Artificial Agents, by David Poole and Alan Mackworth (see esp. Chapter 10)
• The ACM Electronic Commerce conference, for which Kevin Leyton-Brown was program chair in 2012

We have a diverse group of researchers who are interested in ways to represent knowledge, how to reason with this knowledge and how to learn the knowledge. David Poole leads this group with his foundational work on probabilistic first order logic and semantic science. This work on logical and probabilistic reasoning has been of profound and broad impact in the field of artificial intelligence (AI). Holger Hoos is also an important member of this group with his work on satisfiability (SAT) and planning, which has won numerous awards and competitions.

The Computer Vision Lab group began as a part of the Laboratory for Computational Vision, which is well-known for creating and developing robot soccer and SIFT features. Today, we develop algorithms in the areas of image understanding, video understanding, multi-modal (vision + language) modeling, 3D computer vision, human pose estimation, and the use of large generative models for computer vision applications.

The group has three active faculty: Leonid Sigal, Kwang Moo Yi, and Evan Shelhamer. 
Affiliate and adjunct members: Helge Rhodin.
Former and emeritus faculty include: Jim Little, David Lowe, Alan Mackworth, and Bob Woodham.

Members of Computer Vision Lab work closely and collaborate with faculty and students from Graphics, Natural Language Processing and Machine Learning groups.

The group conducts research in many areas of machine learning, with a recent focus on algorithms for large datasets, probabilistic graphical models, and deep learning.

FACULTY

• Kevin Leyton-Brown
• David Poole
• Andrew Roth
• Mark Schmidt
• Leonid Sigal
• Danica Sutherland 
• Michiel van de Panne
• Frank Wood

ASSOCIATE MEMBERS

• Alexandre Bouchard-Côté
• Ben Bloem-Reddy
• Trevor Campbell 

• CVRG Computer Vision Reading Group
• EARG Empirical Algorithmics Reading Group
• NLP Natural Language Processing Reading Group
• HCAI Human-Centered AI Reading Group
• StaR-AI Statistical Relational AI (formerly First-order Probabilistic Inference)
• GT-DT Game Theory and Decision Theory Seminar
• UM-AI User Modeling and Adaptive Interfaces
• MLRG Machine Learning Reading Group
• RLRG Reinforcement Learning Reading Group

LCI Forum

What and Why? The LCI Forum is our monthly meeting, at which we discuss LCI matters and group related issues, share AI and other news, and give brief reports from trips and conferences. An integral part of each LCI Forum is a research talk, given by LCI members, associate members, or visitors. Rumor has it, though, that the real reason behind their popularity is the food. The LCI Fora provide a great opportunity for meeting other members of the lab, hearing about interesting developments, and finally finding out what the person working at the next desk is really working on ;-) The talks are also great opportunities to practice for conference presentations. Standard LCI Forum talks are 30 minutes long, including questions and discussion; we usually give out-of-lab visitors about 45 minutes.

When and Where? LCI Fora run monthly throughout the academic year and during most of the summer. We hold the forum in the ICICS/CS building, at 12pm.

 Please refer to individual faculty pages.

FACULTY

• Giuseppe Carenini
• Jeff Clune
• Cristina Conati
• Kevin Leyton-Brown
• Jim Little 
• Alan Mackworth
• David Poole (Director)
• Mark Schmidt
• Leonid Sigal
• Danica Sutherland
• Michael van de Panne
• Frank Wood

EMERITUS FACULTY

• Robert Woodham
• Alan Mackworth (Founding Director)

ASSOCIATE FACULTY

• Uri Ascher
• Wolfgang Bibel
• Craig Boutilier
• Arnaud Doucet
• Nando de Freitas
• Kurt Eiselt
• Wolfgang Heidrich
• Peter Lawrence
• David Lowe
• Ian Mitchell
• Kevin Murphy
• Raymond Ng
• Siamak Ravanbakhsh
• Ron Rensink
• Steve Wolfman

• Computer Vision and Robotics:
  This is one of the most influential vision and robotics groups in the world. It is this group that created RoboCup and the celebrated SIFT features. The students in this group have won most of the AAAI Semantic Robot Challenges. The group has four active faculty: David Lowe, Jim Little, Alan Mackworth and Bob Woodham. 
• Empirical Algorithmics: 
  Led by Holger Hoos and Kevin Leyton Brown, this research group studies the empirical behaviour of algorithms and develops automated methods for improving algorithmic performance. Work by the empirical algorithmics group at UBC/CS has lead to substantial improvements in the state of the art in solving a wide range of prominent problems, including SAT, AI Planning and Mixed Integer Programming, and won numerous awards. 
• Game Theory and Decision Theory: 
  With Kevin Leyton Brown in the lead, this group has made significant contributions to algorithmic game theory, multiagent systems and mechanism design. David Poole also contributes to this group with his work on decision processes and planning. The research problems attacked by this group are therefore of great importance to e-commerce, auctions and advertising.
• Human-AI Interaction: 
  Led by Cristina Conati and Giuseppe Carenini, this group investigates how  to create human-centered AI-system that humans can trust and collaborate with. A key aspect of this endeavour is enabling AI systems to predict and monitor relevant properties of their users (e.g., states, skills, preferences, needs) and personalize the interaction accordingly, in a manner that maximizes both task performance as well user trust and satisfaction, abiding to principles of transparency, interpretability, predictability and user-control.
• Knowledge Representation and Reasoning: 
  David Poole leads this group with his foundational work on probabilistic first order logic and semantic science. This work on logical and probabilistic reasoning has been of profound and broad impact in the field of artificial intelligence (AI). Holger Hoos is also an important member of this group with his work on satisfiability (SAT) and planning, which has won numerous awards and competitions.
• Machine Learning: 
  With the guidance of Mark Schmidt, this group's vision is to advance the frontier of knowledge in Bayesian inference, Monte Carlo algorithms, probabilistic graphical models, neural computation, personalization, mining web-scale datasets, prediction and optimal decision making. 
• Natural Language Processing: 
  Under the leadership of Giuseppe Carenini and Raymond Ng (Data Management and Mining Lab) this group's vision is to further our understanding of abstactive summarization, mining conversations and evaluative text, natural language generation.
• Programming Languages for Artificial Intelligence (PLAI): 
  Dr. Frank Wood’s PLAI Group performs applied probabilistic machine learning for real-world applications using tools and techniques from deep probabilistic programming. PLAI works with partners across the academic, public and private sectors developing production-quality, open-sourced software for computational neuroscience, image recognition, robotics and AI.