TRIPODS+X:VIS: The DISC Institute Workshop Series on Machine Learning + X.

Lehigh University, Bethlehem PA

Investigators

Abstract

This project encompasses the planning and organization of several specialized workshops that will bring together top experts in multiple areas to shape new and emerging multidisciplinary fields, tapping the tremendous recent surge in the adoption of machine learning tools in various areas of science and engineering. The premise of this project is the need for sophisticated computational tools to analyze data and improve our ability to understand and harness phenomena associated with complex domains such as chemical processes, autonomous robots operating in open and dynamic environments, supply chain optimization involving large organizations with multiple and competing objectives, and cognitive neuroscience bridging electrical brain impulses and high-level functions such as problem solving. Towards this end it is necessary to foster interdisciplinary collaborations and to promote convergent research and develop fertile space for collaborations among industrial, academic, and governmental partners to attack some of the most pressing problems in technology and society. Under the umbrella of the new Institute for Data, Intelligent Systems, and Computation (I-DISC) at Lehigh University, which builds upon the foundation of Lehigh research expertise in areas such as machine learning, optimization, and data-driven decision making, four workshops will be organized that will bring together leading researchers from different research communities that otherwise may not interact. All of these workshops are on newly emerging topics which are expected to gain significant traction in the near future. These topics are as follows: (1) Chemistry, chemical engineering, materials science, and related disciplines where machine learning is used to elucidate and design complex processes (chemical/biological, engineered/natural) or material systems with wide ranging applications addressing grand challenges in energy, health, environment, and water. (2) Robotics, where applications of machine learning, also known as robot learning, has been rapidly growing in recent years, where the main focus has been to develop algorithms to assist robots to acquire novel skill or adapt to their environment through sensing. (3) Supply chain management with the specific focus on applying machine learning models for prescriptive analytics, such as optimization, in contrast to already popular use of machine learning (deep learning) models for predictive and descriptive analytics, such as predicting customer demands. (4) Cognitive Neuroscience with the focus on understanding the brain-cognition-behavior interface, which requires expertise in neuroscience as well as computational modeling, machine learning and big data science in order (a) to enable sophisticated analyses of complex patterns in brain data and (b) to provide insight into how hypothesized brain-level implementations could in fact produce observed behavioral outcomes. This award reflects NSF's statutory mission and has been deemed worthy of support through evaluation using the Foundation's intellectual merit and broader impacts review criteria.