Skip to main content

Electrical Engineering and Computer Science

Artificial Intelligence

Artificial intelligence is a broad field that entails emulating intelligent behaviors, often inspired by human intelligence, in machines. At Vanderbilt, this research encompasses multiple topics including agent-based modeling and simulation, computational creativity, computational game theory, computational models of human problem solving data mining and big data, distributed artificially intelligent algorithms, educational data mining and learning analytics, intelligent learning environments, machine learning, and multi-agent systems.

Robotics, Artificial Intelligence and Computer Graphics


Julie AdamsJulie Adams

Julie Adams - Computational Economics Associate Professor of Computer Science and Computer Engineering

Dr. Adams' distributed artificial intelligence and multiple agent research focuses on coalition formation, which partitions a set of agents into different teams. Choosing the optimal coalition from the set of all possible coalitions is an intractable problem, and her research group has proven that even approximating the coalition formation problem for task allocation is NP-Hard. Adams' research has resulted in a number of coalition formation algorithms and theoretical results, and the Human-Machine Teaming Laboratory is developing the first coalition formation system applicable to a range of uncertain and dynamic domain circumstances. Dr. Adams' cognition algorithm research focuses on providing artificial agents with human like cognitive abilities, such as situation awareness, forgetting, and shared mental models.

Gautam Biswas Gautam Biswas

Professor of Computer Science, Computer Engineering and Engineering Management

Gautam Biswas conducts research in Intelligent Systems with primary interests in modeling and simulation, model-based diagnosis, data mining, and computer-based learning environments (CBLEs) for STEM disciplines. Two primary CBLE's developed by his group are Betty's Brain, a learning by teaching system, and CTSiM, that exploits synergies between computational thinking and science to support learning by model building and simulation. His data mining and learning analytics projects combine model-based and data-driven approaches for diagnosis, prognosis, and discovering student learning behaviors in open-ended learning environments. In the past, he has also developed systems that support planning, scheduling, and resource allocation in real-time distributed environments.

Doug Fisher Doug Fisher

Associate Professor of Computer Science and Computer Engineering
Director of the Vanderbilt Institute for Digital Learning
Faculty Director of Warren College

Doug Fisher's research has previously focused on supervised and unsupervised forms of machine learning; theory, model, and data-driven learning; cognitive models of human classification and problem solving; with applications including cancer informatics and other medical areas, and operations quality control. Increasingly, Doug's research has turned to computational models of creativity; narrative and artificially-intelligent storytellers; and applications in environmental sustainability, particularly in ways that AI can aid in human decision making.

Doug Fisher - Artificial Intelligence

Doug is also employing online and other digital learning tools in the classroom and in campus residential life, notably for AI education. He has been appointed director of the Vanderbilt Institute for Digital Learning and faculty director of Warren College. In these roles, particularly the former, he is investigating the intersection of AI, and computing generally, with the humanities and the arts; leading efforts on educational data mining with data from Vanderbilt's massive, open, online courses (MOOCs); and developing platforms in which Vanderbilt's students and instructors, and other local learning and teaching cohorts, can benefit from learning and teaching in collaboration with global cohorts.

Eugene Vorobeychik Eugene Vorobeychik

Assistant Professor of Computer Science and Computer Engineering

Yevgeniy Vorobeychik's primary research is in computational economics and machine learning, with the dual-goal of predicting economic decisions (descriptive) and developing systems for economic decision support (prescriptive). Economic decisions do not just involve market places, although they are certainly most salient there. Rather, their relevance spans such diverse Eugene Vorobeychik - Artificial Intelligencedomains as cyber security, privacy-preserving data sharing, technology and idea diffusion, epidemiology, and bioinformatics. His group is, therefore, engaged in a broad array of activities, including adversarial machine learning, aimed at improving intrusion detection and prevention systems, predictive agent-based models for forecasting solar panel adoption trends using big data, design of anti-bodies that are robust to rapid virus escape, as well as an array of more traditional mechanism design and analysis problems (such as mechanism design for team formation, sponsored search auctions, and combinatorial auctions), among others.

In addition, Yevgeniy Vorobeychik has a side interest in complex systems theory. His research in this space involved a new theoretical model of complex systems, non-cooperatively optimized tolerance (NOT), which is an alternative to both self-organized criticality (SOC) and highly optimized tolerance (HOT) frameworks, as well as work on the theoretical analysis of the chaos-quiescence transition of Boolean networks.

Affiliated Faculty

Bradley Malin
Associate Professor of Biomedical Informatics, Computer Science

Daniel Fabbri
Assistant Professor of Biomedical Informatics, Computer Science