Download Artificial Intelligence Research Flyer

Research
Artificial Intelligence
COGNITIVE ARCHITECTURES &
COMPUTATIONAL COGNITIVE
SCIENCE
CSE Faculty: John Laird, Satinder Singh Baveja
Affiliated Faculty: David Kieras, Emily Mower Provost
The Artificial Intelligence (AI) program at the University of Michigan comprises a multidisciplinary group
of researchers conducting theoretical, experimental,
and applied investigations of intelligent systems.
Research in cognitive architecture studies the fixed structures underlying cognition. At Michigan, we are exploring
architectural structures to support human-level AI systems,
as well as computational models of human behavior and the
structure of the human brain. All these efforts draw from AI,
psychology, and neuroscience, so that our research is inherently interdisciplinary. Michigan is unique in the breadth of
cognitive architecture research it supports, including active
groups in Soar, EPIC, Act-R, Cognitive Constraint Modeling,
and neutrally-inspired architectures.
MULTIAGENT & ECONOMIC
SYSTEMS
Current projects include research in rational deci-
CSE Faculty: Satinder Singh Baveja, Edmund Durfee,
Michael Wellman
sion making, distributed systems of multiple agents,
Affiliated Faculty: Grant Schoenebeck
machine learning, reinforcement learning, cognitive
Environments with multiple autonomous agents present
specialopportunities and pose distinct challenges for
design and analysis of AI systems. An individual agent
may coordinate with others to improve performance
through intelligent selection of physical, communicative,
and/or computational actions. The agent may also reason
strategically, to predict what the other agents may do based
on their presumed self-interests. A multiagent environment
is effectively a social system, and thus analyzing multiagent
behavior can often be informed by social science. Multiagent
systems research at Michigan considers all perspectives,
from individual agent to social designer.
modeling, game theory, natural language processing, machine perception, healthcare computing, and
robotics.
Research in the Artificial Intelligence laboratory tends
to be highly interdisciplinary, building on ideas from
computer science, linguistics, psychology, economics,
biology, controls, statistics, and philosophy. In pursuing this approach, laboratory faculty and students
work closely with colleagues throughout the University. This collaborative environment, coupled with our
diverse perspectives, leads to a valuable interchange
of ideas within and across research groups.
We design planning and learning algorithms suitable for
multiagent contexts, and methods for analyzing networks
of agents as organizations, economies, and societies. Our
work also spans the range from theory to practice. We
conduct fundamental research in distributed coordination,
algorithmic game theory, and social computing, and apply
our techniques to real-world problems in areas such as
healthcare, electronic commerce, and finance.
Bob and Betty Beyster Building
2260 Hayward Street, Ann Arbor, MI 48109-2121
cse.umich.edu
Research
Artificial Intelligence
MACHINE LEARNING
ROBOTICS
Affiliated Faculty: Al Hero (ECE), Danai Koutra, Emily Mower
Provost (CSE), Susan Murphy (Statistics), Ji Zhu (Statistics)
Affiliated Faculty: Ella Atkins (Aero)
CSE Faculty: Satinder Singh Baveja, Jia Deng, Danai Koutra,
Benjamin Kuipers, John Laird, Honglak Lee, Jason Mars,
Rada Mihalcea, Edwin Olson, Lingjia Tang, Jenna Wiens
Research in machine learning at Michigan encompasses reinforcement, unsupervised, and supervised learning. In reinforcement learning, we focus on building autonomous agents
that can learn to act in complex, sequential, and uncertain environments. In particular, a number of research projects derive
from an interest in building long-lived and flexibly-competent
agents rather than the more usual agents that perform one
complex task repeatedly. In unsupervised learning, we focus
on developing methods for automatically constructing deep
and hierarchical feature representations of high-dimensional
data with applications to computer vision and more generally to sensory information processing and perception. Other
areas of interest include: 1) the integration of multiple learning methods into the cognitive architecture Soar; 2) developing specialized reinforcement learning methods for behavior-change and treatment-design in healthcare settings ;
3) developing specialized methods for learning in large-scale
games and other multiagent problems; and 4) developing
unsupervised, semi-supervised, and supervised learning algorithms for information retrieval and natural language processing as well as for computational biomarkers in medical
domains.
HEALTHCARE COMPUTING
CSE Faculty: Satinder Singh Baveja, Honglak Lee,
Jenna Wiens
The shift towards data driven medicine will have a transformative impact on healthcare. Massive-scale analytical methods
are needed for real-time disease tracking and for discovering
new markers to risk stratify patients for adverse outcomes. The
EECS Department and the Health System at Michigan provide
a unique opportunity to carry out collaborative research at the
cutting edge of machine learning, data mining, and medicine.
CSE Faculty: Satinder Singh Baveja, Jason Corso,
Edmund Durfee, Chad Jenkins, Benjamin Kuipers,
John Laird, Edwin Olson
We are investigating both theoretical and practical aspects of
robots, including aerial, underwater, space, and terrestrial systems. Key areas include: 1) integration of strategic and tactical
planning and optimization algorithms to enable robust robot
control in the presence of system failures and environmental uncertainties; 2) simultaneous localization and mapping
for mobile robots; 3) sensor processing algorithms, including
feature matching, object detection, classification, and recognition; 4) AI methods from machine learning, cognitive architectures and multiagent systems to build autonomous robots.
COMPUTER VISION
CSE Faculty: Jia Deng, Chad Jenkins, Benjamin Kuipers,
Honglak Lee, Edwin Olson
We explore a number of critical problems in the area of
computer vision. We focus on the analysis and modeling of
visual scenes from static images as well as video sequences.
Our research goals include: i) the semantic understanding of
materials, objects, and actions within a scene; ii) modeling the
spatial organization and layout of the scene and its behavior in
time. The algorithms developed in this area of research enable
the design of machines that can perform real-world visual
tasks such as autonomous navigation, visual surveillance, or
content-based image and video indexing.
NATURAL LANGUAGE PROCESSING
& INFORMATION RETRIEVAL
CSE Faculty: Rada Mihalcea
Affiliated Faculty: Steve Abney (Linguistics),
Jason Mars (CSE), Qiaozhu Mei (SI), Lingjia Tang (CSE)
We are interested in large-scale natural language processing,
including information extraction, text summarization, question answering, and applications to other fields such as political science, bioinformatics, and social science. Our techniques
range from semantic analysis and parsing to semi-supervised
learning and graph-based methods. Some current projects include the automatic generation of surveys of scientific literature, protein network extraction from text, the extraction of attitude and sentiment in online social network discussions, the
study of rumor propagation on Twitter, the dynamics of political speeches in US congress, and the creation of networks of
genes, diseases, and vaccines.
Bob and Betty Beyster Building
2260 Hayward Street, Ann Arbor, MI 48109-2121
cse.umich.edu
Research
Artificial Intelligence
ASSISTIVE TECHNOLOGY
CSE Faculty: Satinder Singh Baveja, Edmund Durfee,
Walter Lasecki, Emily Mower Provost
Artificial Intelligence techniques can significantly enhance
technology that enables people with cognitive and/or physical
impairments to live more autonomously. At Michigan, we employ automated planning, temporal reasoning, machine learning, probabilistic inference, and crowdsourcing techniques
to create assistive technologies. Examples of target systems
include ones that provide flexibly timed reminders of daily
activities to people with memory impairment; that automatically adapt a computer interface to meet the needs of a person
with visual or fine-motor impairment; that answer visual questions about the world for a blind person; or that monitor the
behavior of a person at home, to identify emerging functional
problems.
CONSTRAINT-BASED REASONING
CSE Faculty: Edmund Durfee, Michael Wellman
Many interesting problems can be modeled as sets of constraints that must be satisfied and/or of preferences that should
be optimized. Constraint-based reasoning studies both formalisms for representing constraints and preferences, and algorithms for efficiently finding solutions to problems encoded
in these formalisms. Research on constraint-based reasoning
at Michigan has focused on a variety of topics, including temporal reasoning, Boolean satisfiability, and Satisfaction Modulo
Theory (SMT) solving, as well as on applications to varied domains such scheduling, interface design, and the verification of
integrated circuits.
HUMAN COMPUTATION &
CROWDSOURCING
CSE Faculty: Walter Lasecki
Human computation incorporates human intelligence into
algorithmic processes. It is, at its core, the study of structured
work. While workflow, process management, and organizational theory has been developed in great depth previously,
the introduction of computer science and computational theory has given us a new lens through which to view organized
human efforts, and combine it with the efforts of automated
systems. Crowdsourcing — the practice of making an open
call to a group of workers to complete a task, often through
social computing channels — has created the opportunity to
create large-scale human computation systems that are far
more capable than current automated systems, but are still
available on-demand, at a moment’s notice. At Michigan, we
are advancing the frontiers of what can be accomplished with
human computation and crowdsourcing: exploring how to
create systems that respond intelligently, in real-time, and with
consistency over time.
Bob and Betty Beyster Building
2260 Hayward Street, Ann Arbor, MI 48109-2121
cse.umich.edu
Research
Artificial Intelligence
FACULTY IN ARTIFICIAL INTELLIGENCE
Jacob Abernethy
Assistant Professor
jabernet
3765 Beyster Bldg
Satinder Singh
Baveja
Professor
baveja
3749 Beyster Bldg
Jason Corso
Associate Professor
jjcorso
4227 EECS
Jia Deng
Assistant Professor
jiadeng
3640 Beyster Bldg
Edmund Durfee
Professor
durfee
3745 Beyster Bldg
Chad Jenkins
Associate Professor
ocj
3644 Beyster Bldg
Benjamin Kuipers
Professor
kuipers
3741 Beyster Bldg
John Laird
John L. Tishman
Professor of
Engineering
laird
3753 Beyster Bldg
Walter Lasecki
Assistant Professor
wlasecki
2636 Beyster Bldg
Honglak Lee
Associate Professor
honglak
3773 Beyster Bldg
Jason Mars
Assistant Professor
profmars
4705 Beyster Bldg
Rada Mihalcea
Professor
mihalcea
3769 Beyster Bldg
Emily Mower
Provost
Assistant Professor
emilykmp
3620 Beyster Bldg
Edwin Olson
Associate Professor
ebolson
3737 Beyster Bldg
Lingjia Tang
Assistant Professor
lingjia
4609 Beyster Bldg
Michael Wellman
Professor
wellman
3757 Beyster Bldg
Jenna Wiens
Assistant Professor
wiensj
3640 Beyster Bldg
Bob and Betty Beyster Building
2260 Hayward Street, Ann Arbor, MI 48109-2121
cse.umich.edu
Research
Artificial Intelligence
AFFILIATED FACULTY
Steven Abney - Linguistics
Matthew Johnson-Roberson - Naval and Marine Engineering
Ella Atkins - Aerospace Engineering
Richard Lewis - Psychology and Linguistics
Laura Balzano - Electrical and Computer Engineering
Qiaozhu Mei - School of Information
Dmitry Berenson – Electrical and Computer Engineering
Kayvan Najarian - Computational Medicine and
Bioinformatics
Ceren Budak - School of Information
Kevyn Collins-Thompson - School of Information
Ryan Eustice - Naval and Marine Enigineering
Alfred Hero - Electrical and Computer Engineering
Danai Koutra - Computer Science and Engineering
Mark Newman - School of Information
Long Nguyen - Statistics
Thad Polk - Psychology
Ambuj Tewari - Statistics
Bob and Betty Beyster Building
2260 Hayward Street, Ann Arbor, MI 48109-2121
cse.umich.edu