Core Faculty
 
 
Dr. Bar-Joseph's research interests include Computational Biology, Bioinformatics and Machine Learning: Analyzing time series gene expression data, optimal leaf ordering, genetic regulatory networks. Distributed Computing: Large scale dynamic distributed systems, probabilistic consensus. Computer Graphics and Image Processing: Sound, image and movie texture synthesis from examples.
 
     
 
Dr. Cohen's research interests include information integration and machine learning, particularly information extraction, text categorization and learning from large datasets. He holds seven patents related to learning, discovery, information retrieval, and data integration, and is the author of more than 100 publications.
 
 
 
Dr. Eddy concentrates on statistical methods for analyzing images, particularly time series of images. His imaging research began with functional magnetic resonance imaging but has expanded to include cDNA microarrays, gel electrophoresis, positron emission tomography, and video.
 
 
 
Professor Faloutsos is working in databases. His research interests include data mining for streams and sensors; pattern discovery in large graphs, and indexing methods for multimedia and biological databases.
 
 
 
Dr. Fienberg's principal research interests lie in the development of statistical methodology, especially for problems involving categorical variables. He is currently working on a number of different aspects of data disclosure limitation and has married these to his long-standing interest in categorical data problems.
 
 
 
Dr. Ghahramani is interested in all aspects of statistical machine learning, including graphical models, Bayesian statistics, non-parametric and kernel methods, semi-supervised learning, and decision making under uncertainty. He has worked in computational neuroscience focusing on human sensorimotor control, and on applications of machine learning to bioinformatics and information retrieval. He also has an appointment at the University of Cambridge.
 
 
 
Dr. Gordon is interested in multiagent learning and planning, statistical models of difficult data (examples include natural-language text and maps of a robot's surroundings), game theory, and computational learning theory.
 
 
 
Dr. Guestrin's research focuses on developing efficient methods for control, inference and learning in large-scale problems, such as sensor networks, multiagent systems and relational data analysis. His research aims to combine techniques from artificial intelligence, machine learning, optimization theory and statistics to tackle highly uncertain complex problems.
 
 
 
Professor Kass has for many years studied the Bayesian approach to statistical inference, and has contributed to the development of Bayesian methods and their computational implementation. He has recently become interested in statistical problems in neuroscience, especially in the analysis of signals coming from single neurons and from multiple neurons recorded simultaneously.
 
 
 
Dr. Lafferty's research interests lie in statistical methods for natural language processing and information technologies, statistical learning algorithms, and coding and information theory.
 
 
 
Professor Maxion's research focuses on ultra-dependability of mission-critical systems, which requires automated, unsupervised detection and diagnosis of unanticipated anomalies, faults, and other pattern-based events in super-large, high-dimensional datasets (typically monitored from continuous processes).
 
 
 
Dr. Mitchell works on new learning algorithms, such as methods for learning from labeled and unlabeled data. Much of his research is driven by applications of machine learning such as understanding natural language text, and analyzing fMRI brain image data to model human cognition.
 
 
 
Prof. Montgomery works on the application of data mining and statistical analysis to solve marketing problems. His research has focused on developing price and promotional strategies from purchase transaction data and the analysis of clickstream data to predict consumer behavior in online environments.
 
 
 

Currently on Leave of Absence as Director of Google Pittsburgh.

Professor Moore has worked with robots that learn, factories than learn and supply chains that learn. His current primary research interest concerns "cached sufficient statistics": very efficient algorithms for statistical learning and decision making from enormous data sources.
 
 
 

Dr. Murphy's principal interest is in computational biology, the application of computers to solve problems in biology. In particular, he is interested in the application of machine learning methods to biological images (especially microscope images depicting subcellular location), the application of active learning methods for analyzing and modeling complex biological phenoma, and the development of knowledge bases relating to protein properties from both text and images in online sources.

 
 
 
Molecular evolution is a stochastic computational process that has been running on massively parallel hardware for some 10^17 seconds now, and which has resulted in many amazing local maxima along the way. The rapidly growing DNA and protein databases present a historic opportunity to model evolution at an unprecedented quantitative level, with enormous impact on medicine as well as on our fundamental understanding of life. To that end, we combine statistical and computational methods to derive biological explanations and pharmacological predictions.

Viruses are the simplest known self-replicating computational system. They also happen to be the leading emerging threat to humanity in the 21st century. Fortunately, the new understanding of life in general and viruses in particular as digital programs opens the door to computational methods of defending against these threats. In collaboration with virologists and genomicists at the University of Pittsburgh, we combine biological analysis with statistical learning methods to better understand viral evolution and accelerate vaccine development.
 
 
 
Dr. Scheines' research interests focus on causal inference from statistical data. He is particularly interested in improving upon the reliability of regression in detecting causation, and in automatically constructing causal models that involve latent, or unobserved variables.
 
 
 
Dr. Seidenfeld works at the interface between philosophy and statistics, often concerning myself with problems that involve multiple decision makers. For example, in collaboration with Mark Schervish and Jay Kadane (of CMU's Stats. Dept), we have relaxed the norms of Bayesian theory to permit a unified standard, both for individuals acting as separate decision makers and collectively, in forming a cooperative "group" agent. By contrast, this is an impossibility for strict Bayesian theory.
 
 
 
Professor Sweeney's research spans the fields of anonymity in data, data profiling, data linkage, intelligent tutoring and learning systems and knowledge representation. She is involved in the development of a new area of computer science that she terms computational disclosure control.
 
 
 
Professor Wasserman's research interests include nonparametric inference, multiple testing, asymptotic theory, causality, and applications to astrophysics and genetics.
 
 
 
Dr. Xing's principal research interests lie in the development of machine learning and statistical methodology; especially for building quantitative models and predictive understandings of the evolutionary mechanism, regulatory circuitry, and developmental processes of biological systems, and for building computational intelligence systems involving automated learning, reasoning, and decision-making in open, evolving possible worlds.

Currently the following major themes are studied in his group: 1) graphical models, Bayesian approaches, inference algorithms, and learning theories for analyzing and mining high-dimensional, longitudinal, and relational data; 2) computational and comparative genomic analysis of biological sequences, systems biology investigation of gene regulation, and statistical analysis of genetic variation, demography and linkage (to diseases); and 3) application of statistical learning in text/image mining, vision, and machine translation.
 
 
 
Dr. Yang's research has centered on statistical classification methods and their applications to a variety of challenging problems in the real world, including automated text categorization and clustering, corpus-based learning for cross-language information retrieval, novel-event detection and tracking from sequential data, information extraction from Internet/Web environments, intelligent email filtering and prioritization, and statistical reasoning based on protein/gene expressions.