Snehasis Mukhopadhyay Ph.D.

Professor, Computer Science


BE - Electronics and Telecommunications Engineering, Jadavpur University, 1985
ME - Systems Science and Automation, Indian Institute of Science, 1987
MS - Electrical Engineering, Yale University, 1991
PhD - Electrical Engineering, Yale University, 1994

Awards & Honors

2017 - Trustee Teaching Award, IUPUI

1996 - CAREER Award, National Science Foundation

1995 - NET (Network for Excellence in Teaching) Award, IUPUI

1987 - Khambhati Memorial Gold Medal, Indiana Institute of Science

1979-1985 - National Merit Scholarship of the Government of India

Current Research

Snehasis Mukhopadhyay has been conducting research for over 25 years in the areas of Intelligent Systems, Machine Learning, Data Mining, and Biomedical Informatics. Below are brief descriptions of two representative examples of his current projects:

(i) Machine Learning

Title: Fast Reinforcement Learning Using Multiple Models and State Decomposition

Source of support: National Science Foundation (NSF)

Collaboration: Yale University

Abstract: Intelligent behavior in both natural and man-made systems consists in being repeatedly successful in achieving some desired goals in diverse, observably different situations on the basis of past experience. Learning is central to such behavior, since in both cases, mechanisms have to exist which yield rapid improvement with minimum a priori information. In fact, organizing, coordinating, and executing diverse tasks such as manipulation of effectors, obstacle avoidance, path planning, scene analysis, tracking which are common to both classes of systems, involve learning. Ever since the time of Estes, mathematical learning theory has treated learning and performance as stochastic processes. Asymptotic properties of such processes have been used both descriptively and prescriptively in models of learning. This project deals with a class of such learning systems of great interest at present time. The slow speed of convergence of stochastic learning schemes is well recognized by the learning community. Equally well known is the fact that this limits the applicability of the schemes in many practical situations. The principal objective of this project is to address this important problem using two different methods: (a) the use of multiple identification models, and (b) decomposition of high dimensional state and action spaces. The project elaborates on the different ways in which (a) can be used to improve convergence. In (b) multiple agents with lower dimensional state spaces are used in place of high dimensional state and action spaces to overcome "the curse of dimensionality". Also, judicious infrequent communication between agents is also proposed to speed up convergence. An important off-shoot of this research is the possibility quantifying the trade-off between learning speed and the quality of the "learned solutions". The research described above will find application in situations where rapid learning is mandatory. One such area is the control of a fleet of Plug-in, Hybrid, Electric Vehicles (PHEVs). Given a fleet of vehicles, the objective reduces to a complex optimization problem of orchestrating switching between internal combustion engines and electric engines, under a variety of constraints.

(ii) Intelligent Systems

Title: A secure decision support system for coordination of adaptation planning among Food, Energy, and Water actors in the Pacific Northwest

Source of Funding: National Science Foundation (NSF)/United States Department of Agriculture (USDA)

Collaboration: Oregon State University

Abstract: Given the increasingly strong evidence for emerging climate change and economic trends, coordination of adaptation decisions for managing limited natural resources - such as water and arable land - in food, energy, and water (FEW) sectors, are expected to become increasingly critical. The goal of this project is to establish a novel, intelligent, secure, and human computation-based decision support system that will enable local and regional community actors to coordinate and co-identify robust adaptation decisions for natural resources management in FEW systems, when chronic and/or acute physical and socio-economic perturbations occur. While most studies investigate adaptation at global or regional scale, this study focuses on adaptation to climate-related and policy related perturbations in local FEW systems (where communities are most invested). The PIs will collaborate to investigate five specific interdisciplinary research objectives with pertinent research questions, one outreach objective, and one education objective. In summary, the approach will first develop formulation of interlinked adaptation decisions in interlinked FEW sub-systems, stakeholder-related parameters, and perturbation scenarios for the testbed site in Hermiston, Oregon. Next, novel mathematical and computational approaches for human computation-based Multidisciplinary Design Optimization methods and trust management models will be created, and tested for their effectiveness in enabling coordination of decisions and stakeholder participation in a secure design environment. A tightly integrated plan for research and education is enabled by the participation of undergraduate and high school underrepresented and minority students, along with stakeholder groups in various research tasks.

Related Project Website: