Research in Machine Learning, Neural Computation, and Statistical Inference
at the University of Colorado, Boulder

The University of Colorado at Boulder provides an outstanding interdisciplinary environment for research and graduate training in Machine Learning, Neural Computation, and Statistical Inference in the fields of Artificial Intelligence, Cognitive Science, Bioinformatics, and Engineering. Our research spans topics including:

While these research topics are diverse and involve different subsets of the faculty, faculty interactions lead to many synergies among the topics.

Faculty

Department of Aerospace Engineering

Nisar Ahmed
Collaborative human and autonomous robot vehicle systems; dynamic state estimation and sensor fusion; supervisory control and decentralized coordination in networked systems; statistical system identification, machine learning and artificial intelligence for aerospace applications

Department of Applied Math

Stephen Becker
Optimization, compressed sensing, matrix completion, nonnegative matrix factorization, and physical applications (e.g., medical imaging, renewable energy)
Jem Corcoran
Markov chain Monte Carlo methods, recovering Bayes networks from data, particle filtering and target tracking
Vanja Dukic
Bayesian modeling, inference, computational statistics, with applications to a variety of fields ranging from medicine and ecology to risk and insurance
Manuel Lladser
discrete probability, analytic combinatorics, asymptotic analysis, embedding techniques; computational biology, RNA secondary structure prediction, extrapolation of microbial communities

Department of Civil, Environmental, and Architectural Engineering

Michael Brandemuehl
Adaptive control for building systems; simulation and testing of energy systems; HVAC systems
Moncef Krarti
Building systems modeling with neural networks and statistical techniques
Gregor Henze
Model-based predictive optimal control and model-free reinforcement learning control of building energy systems and building thermal mass; time series prediction and forecasting; building occupancy detection using distributed belief networks; whole building fault detection and diagnosis

Department of Computer Science

Elizabeth Bradley
Artificial intelligence approaches to understanding and modeling nonlinear dynamics and chaos; nonlinear control
Aaron Clauset
complex networks; statistical forecasting; stochastic processes; massive data sets; computational biology and biological computation; engineering complex systems
Sidney D'Mello
affective computing, attentional computing, intelligent learning environments, speech and language processing, human-computer interaction, computational models of cognition
Rafael Frongillo
theoretical machine learning and economics, primarily focusing on domains such as information elicitation and crowdsourcing which involve the exchange of information for money; research draws on techniques from convex analysis, game theory, optimization, and statistics.
Larry Hunter
Development and application of advanced computational techniques for biomedicine, particularly the application of machine learning and statistical inference techniques to high-throughput molecular assays. Also, automated processing of biomedical texts, inference of metabolic and signaling pathways, and neurobiologically and evolutionarily informed computational models of cognition.
Dan Larremore
Using the methodology of network science, dynamical systems, and statistical inference to solve problems in social and biological systems
James Martin
Statistical approaches to machine translation, spoken language help systems, and the generation of instructional texts; metaphor understanding
Rebecca Morrison
High-dimensional Bayesian modeling and model inversion; Probabilistic graphical models and sparsity of Markov random fields; Mathematical representations of model inadequacy; Calibration, validation, and uncertainty quantification for predictive models
Michael Mozer
Improving human learning, performance, and decision making via machine learning techniques and computational models of human perception and cognition
Martha Palmer
Natural language processing and knowledge representation; computational linguistics; machine translation; annotation
Ben Shapiro
Philosophical aspects of machine learning; application of ML methods to human-computer interfaces
Chenhao Tan
Social aspects of language--how language influences social interaction and how language functions as a lens on social dynamics and human culture; multi-community engagement--how a person interacts with multiple communities and how communities relate to each other
Wayne Ward
Spoken language understanding, conversational speech systems, summarization, integrating stochastic and rule-based language models

Department of Electrical and Computer Engineering

Francois Meyer
Unsupervised learning; visualization and interpretation of high dimensional data; signal processing, applications of machine learning; analysis of fMRI and EEG data
Kelvin Wagner
Applying organizational principles of neural networks in the brain to artificially constructed adaptive systems made from optical devices. The neurons are implemented using custom integrated circuits that incorporate photodetectors and light modulators, while the adaptive synapses are formed as dynamic holographic interconnection gratings whose strength grows in proportion to the correlated activity of the source and destination neurons. Architectures, devices, and simulations have been developed for self-aligning multilayer holographic optical learning systems for the implementation of optical back propagation and optical competitive learning, which are prototypical supervised and unsupervised learning algorithms.

Department of Information Science

Michael Paul
Develops methods for analyzing and understanding data using machine learning, statistical modeling, and natural language processing. Focus on health informatics and epidemiology, using new and transformative sources of data.
Danielle Albers Szafir
Develops interactive visualization systems and techniques for exploring large and complex data in domains ranging from biology to the humanities. Research focuses on increasing the scalability and comprehensibility of information visualization by quantifying perception and cognition for design.

Department of Integrative Physiology

Alaa Ahmed
Biomechanical and sensorimotor processes underlying human movement control and decision making. Investigates the effects of instability and uncertainty on the control of movement and posture using a combination of methodologies including virtual reality, robotic interfaces, kinetic and kinematic analyses, and computational modeling.

Department of Linguistics

Mans Hulden
Computational linguistics; formal language theory, machine learning and natural language processing for less-resourced languages
Lise Menn
Child language acquisition; neurolinguistics; aphasia

Department of Psychology

Marie Banich
cognitive neuroscience of attention, memory, and executive function; human neuropsychology
Eliana Colunga
Language development, concept acquisition, statistical learning; improving child vocabulary learning; methodologies include developmental studies and computational modeling
Tim Curran
Human learning and memory from a cognitive neuroscience perspective, using EEG and ERP measures to predict and improve human learning
Matt Jones
human learning and knowledge representation, with emphases on categorization, similarity, generalization, relational representations, and sequential decision making
Walter Kintsch
Psychological theories of comprehension, discourse processing, and higher reasoning based on statistical approaches, including parallel relaxation search and latent semantic analysis, a technique that derives estimates of relatedness from very large text corpora.
Yuko Munakata
Memory, attention, and controlled processing, assessed through computational models and studies of behavioral dissociations in children and adults
Randy O'Reilly
Biologically constrained computational modeling of cognitive phenomena. Currently focusing on interactions between hippocampus, prefrontal cortex, and posterior association cortex in episodic memory phenomena, and on developing a biologically plausible yet computationally powerful model of long-term learning in the neocortex.
Tor Wager
Application of machine learning methods to develop fMRI-based biomarkers for clinical outcomes (e.g., pain); multivariate pattern analysis, multivariate brain connectivity, neural regulation of pain and emotion.

Graduate Study

Applications for graduate study and further information about graduate programs can be obtained from the home page of the relevant department. Those with an interest in cognitive science and cognitive neuroscience should visit the Institute of Cognitive Science home page.

Support is generally available for Ph.D. students in the form of teaching and research assistantships.

In addition to providing an exciting research environment, the Boulder area offers an exceptional quality of life. Spectacularly situated at the foot of the Rockies, Boulder provides a wide variety of extraordinary outdoor activities and an average of 330 sunny days per year. Together with Denver, Boulder also affords a broad range of cultural opportunities.

Courses

See Machine Learning Courses at the University of Colorado for more information on current offerings. Here is a sample of of recent course offerings relating to neural and statistical computation. Consult department home pages for more information about course topics.


This page is maintained by Mike Mozer