UC Irvine ICS Artificial Intelligence ICS Logo

Artificial Intelligence

Research in Artificial Intelligence (AI) is aimed at understanding the computational mechanisms that underlie intelligent behavior, and at designing computational systems that exhibit it. The AI group at ICS is involved in research on machine learning and knowledge discovery, deductive and probabilistic reasoning, constraint satisfaction techniques, neural networks and cognitive architectures, sophisticated image and signal processing, scientific reasoning in domains such as molecular biology, medicine and space science, intelligent web-based agents, and the psychological investigation of human learners. The group is interested in basic research into the fundamental principles of intelligence; the methods by which knowledge is acquired, summarized, organized, and utilized to solve complex problems; the construction of computational artifacts that support algorithmically, cognitively, or conceptually challenging tasks and embody behavior associated with intelligent systems; and applications that confront intelligent systems with real-world tasks.

AI papers from UCI

Machine Learning

Machine learning investigates the mechanisms by which knowledge is acquired through experience. Research at UCI spans the spectrum of models for learning, including those based on statistics, logic, mathematics, neural structures, information theory, and heuristic search algorithms.

Our research involves the development and analysis of algorithms that identify patterns in observed data in order to make predictions about unseen data. New learning algorithms often result from research into the effect of problem properties on the accuracy and run-time of existing algorithms.

We investigate learning from structured databases (for applications such as screening loan applicants), image data (for applications such as character recognition), and text collections (for applications such as locating relevant sites on the World Wide Web). UCI also maintains the international machine learning database repository, an archive of over 100 databases used specifically for evaluating machine learning algorithms.

Knowledge Discovery and Data Mining

Databases with millions of records and thousands of fields are now common in business, medicine, engineering, and the sciences. The problem of extracting useful information from such data sets is an important practical problem. Research on this topic focuses on key questions such as how can one build useful descriptive models that are both accurate and understandable? Probabilistic and statistical techniques in particular, play a key role in both analyzing the inference process from a theoretical viewpoint and providing a principled basis for algorithm development. Ongoing projects include the integration of image and text health-care data for finding diagnostic rules, automated analysis of time-series engineering data from the Space Shuttle, and discovery of recurrent spatial patterns in historical pressure records of the Earth's upper-atmosphere.

Automated Reasoning; Constraint networks and Probabilistic networks.

Automated reasoning investigates methods by which knowledge is represented and used to emulate human-like thought processes. Although most reasoning tasks were found to be computationally hard, it is believed that approximation methods based on tractable models can effectively cover a significant portion of intelligent activities. Accordingly, research at UCI is focused developing flexible and expressive representations that accommodate efficient reasoning, by:

Research at UCI has focused on constraint networks and probabilistic networks as the primary models for addressing these issues. These frameworks unify and cut across many traditional areas in Artificial Intelligence. Constraint processing is a paradigm for formulating knowledge in terms of a set of existing or desired relationships among entities, without specifying methods for achieving such relationships. A variety of constraint processing techniques have been developed and applied to diverse tasks such as vision, design, diagnosis, truth maintenance, scheduling, default reasoning, spatio-temporal reasoning, logic programming, and user interface. Belief networks provide a formalism for reasoning about partial beliefs under conditions of uncertainty. They capture causal influences between linked variables and are widely applicable for knowledge diffusion, diagnosis, abduction and planning. The current focus at UCI is on application areas such as diagnosis, planning and scheduling and on probabilistic decoding.

Faculty working in Automated reasoning

Rina Dechter
Padhraic Smyth

Useful links

Constraint Programming

Brain Modeling

The mind is what the brain does, and the brain is now coming to be understood as a machine. As such, the anatomical architectures and physiological operation of specific brain circuitries can be analyzed formally. Such investigations have led to the identification of mechanisms by which these biological design features can dictate the recognition, memory and motor capabilities of these circuits. Of primary scientific interest is increasing our knowledge of how the brain actually works; also of interest is the engineering application of such knowledge to the construction of novel devices that have brainlike abilities. Modeling of particular brain circuits has led to the derivation of novel and powerful computational devices for tasks ranging from signal classification, temporal signal processing and memory storage to motor coordination and robotics. As might be expected of circuitry evolved to process complex environmental information, these devices have been shown to equal or outperform the best extant engineering approaches on a range of difficult applications such as radar detection and medical image analysis. Devices based on this work are now installed and used at U.S. Navy and other laboratories, and are under commercial development for signal processing uses in a number of applications domains.

Biomedical Computing: Computational Biology and Medical Informatics

There are a number of significant problems in biology and medicine for which computational approaches can yield important insights. The world-wide efforts to construct databases of protein and small molecule structures, DNA sequences, metabolic pathways, regulatory mechanisms, pharmaceutical structures and activities, patient response data, etc., have created many opportunities for intelligent systems. Central questions include: What function is encoded in a protein sequence? What structure will it fold into? How can we make better pharmaceutical drugs? What factors effect patient response to treatment? Partial solutions to these problems have been found using extensions of research on knowledge representation, search, and learning.

ICS faculty are involved in a project to develop a knowledge-based systems for recommending a customized multiple-drug therapy for HIV infected patients. We are also exploring an approach to creating knowledge-based systems by learning from patient data and have identified guidelines for screening for forms of dementia such as Alzheimer's disease. We have developed knowledge-based approaches to protein structure prediction, and implemented novel sequence-structure search algorithms and recognition methods. We are modeling DNA mutation and repair in connection with cancer-related studies.

The biomedical domain is a rich source of application problems on which to test AI methods, and we welcome inquiries from academic and industrial colleagues with interesting biomedical research problems amenable to an AI-based computational approach. AI methods are applicable to many of the questions in computational biology.


Dechter, Rina dechter@ics.uci.edu 949/824-6556 424E CS
Granger, Rick granger@ics.uci.edu 949/824-6360 337 CS/E
Kibler, Dennis kibler@ics.uci.edu 949/824-5951 414D CS
Lathrop, Richard rickl@ics.uci.edu 949/824-4021 464 CS
Pazzani, Michael pazzani@ics.uci.edu 949/824-7405 444 CS
Smyth, Padhraic smyth@ics.uci.edu 949/824-2558 414E CS

Information and Computer Science
University of California, Irvine , CA 92717-3425
September 29, 1998