Hey Siri, how can scientists and engineers apply machine learning (ML) to their own research?

OK Google, where can I get a hands-on tutorial on ML?

Alexa, who else at Virginia Tech is studying ML?

Instead of asking smart devices, you can get these questions and more answered by humans at an upcoming workshop hosted by the Macromolecules Innovation Institute (MII), an interdisciplinary polymer research center at Virginia Tech.

The workshop, titled “Learning about Machine Learning,” will provide an opportunity for faculty, staff, and students to learn from Virginia Tech faculty who already use machine learning in their research.

“Learning about Machine Learning” is a pre-conference workshop tied to MII’s institute-wide technical conference and review from Nov. 4-6.

The ML workshop will take place at the Inn at Virginia Tech from 9 a.m. to noon on Nov. 4. It is free and open to all Virginia Tech faculty, staff, and students, and no registration is required.

“Machine learning is a tool every scientist and engineer will have to use in the coming decade,” said MII Director Tim Long, who is also a professor of chemistry. “This workshop is meant to enable students and faculty to understand the potential implications of machine learning in their everyday research and to increase our awareness of the possibilities for machine learning to advance or accelerate discovery.”

Headlining the program is Luke Achenie, a professor of chemical engineering, who will give a tutorial/lecture on ML in Python. Other faculty presenters will include Shengfeng Cheng (physics), Hongliang Xin (chemical engineering), and Anuj Karpatne (computer science).

Sanket Deshmukh, an assistant professor of chemical engineering and an affiliated faculty member of MII, helped organize the workshop program.

“The audience will be exposed to several fundamental concepts in ML and hands-on tutorials to apply ML for problems with different levels of difficulties,” Deshmukh said. “In addition, they will also learn the current applications, challenges, and future perspectives of ML in studying both soft and hard materials.”

Long said he hopes this workshop will help faculty become more competitive in proposal writing if they can incorporate some of these ML concepts. But he also said a half-day workshop is not nearly long enough to tackle such a complex topic, and he hopes to see more ML workshops across campus. 

“This is a first step in a broader initiative for MII to gain awareness and complement our efforts in computational tools for discovery,” Long said. “It’s not going to be a one-and-done initiative for MII.”