Machine Learning and Data Science

illustration of cloud computing and data

How can we best utilize real-time data generated by various sensors on a factory floor to monitor the health and safety of systems, finely control machine performance, ensure product quality control and improve the manufacturing process overall? That’s just one of the questions we’re exploring through the integration of machine learning and data science to the world of manufacturing. We’re also applying these overarching technologies to robotics and biomechanics to innovate in ways previously not possible.

In contrast to the historical way that we understand the mechanisms that govern the behavior of systems through physical laws, machine learning means we’re connecting machines to directly learn from real data, without imposing limits based on the underlying physics. This approach leads to better results in everything from manufacturing efficiencies to facial recognition to autonomous vehicle performance. We’re focused on how to effectively use data in a timely manner so improvements can be made in a matter of minutes. 

We’re teaming with industry to delve into timely solutions that harness data for improved processes.

Institutes, centers and labs related to Machine Learning and Data Science

Rethink Robotics Baxter robot

Integrated Robotics Center

Using a cross-discipline approach to bring creativity, knowledge and expertise to the creation of robotic systems, with a specific focus on exploration, intelligence, movement, manufacturing and health care

Faculty who conduct research in Machine Learning and Data Science

Profile Photo

Robert Gao

Department Chair, Mechanical and Aerospace Engineering
Cady Staley Professor of Engineering
Professor, Mechanical and Aerospace Engineering

Develops multi-physics sensing and stochastic modeling methods for improving observability in dynamical systems

Profile Photo

Bo Li

Assistant Professor, Mechanical and Aerospace Engineering

Develops HPC-based computational methods for the dynamic behavior and failure processes in materials and structures under extreme conditions

Profile Photo

Roger Quinn

Arthur P. Armington Professor of Engineering
Professor, Mechanical and Aerospace Engineering
Director, Biologically Inspired Robotics

Develops neural and mechanical models of animals and uses data to design and control robots and exoskeletons