Remote Career Coaching Support: Our team is offering 1:1 appointments (via Webex or phone) to support students and alumni in their career exploration and job/internship search. Schedule appointments in UMBCworks.

UMBCworks: UMBC’s official career platform where you can make appointments, access events, as well as hundreds of jobs and internship postings.

Jump to:
Hours & Contact Details
Remote Appointments
Resume & Cover Letter Reviews
Workshops & Events
Career Center Practicums
Internship & Job Search Support
Virtual Resources

Theoryful Machine Learning
in the Chemical Sciences

Prof. Tyler R. Josephson

ATOMS Lab: AI & Theory-Oriented Molecular Science
Chemical, Biochemical & Environmental Engineering, UMBC

1:00-2:00 pm, 5 February 2021
online via webex

Modern machine learning (ML) algorithms have achieved remarkable success in “theoryless” problems of image recognition and natural language processing. When these algorithms find applications in “theoryful” domains like physical sciences, they frequently benefit from the incorporation of domain knowledge into the ML architecture, whether enforcing constraints or symmetries or interpreting neural networks as physical systems.

The chemical sciences have many “theoryful” ML problems. In this talk, I will discuss three projects in which we leverage background theory when designing and adopting ML algorithms. In the first project, we use classical thermodynamics to derive a method to characterize mixture properties in molecular simulations and show that multiple linear regression (with no bias) is the formally correct and thermodynamically consistent model for fitting and predicting these properties. We recently developed an alternative proof from statistical thermodynamics that gives the same result, and we provide evidence that nonlinear methods provide no improvement in performance. In the second project, we perform high-throughput molecular simulations of adsorption (when molecules from a gas or liquid stick on the surface or in the pores of a material), which we analyze using neural networks. We derive a correspondence between theories of multicomponent adsorption and the self-attention mechanism in the transformer architecture and show how the theory-inspired architecture has improved generalization over the multilayer perceptron.

In the final project, I will share work on symbolic regression, in collaboration with the Mathematics of AI department at IBM. In symbolic regression, given a data set, a search through some “space of possible equations” identifies accurately-fitting and parsimonious equations that can be easily inspected by humans. We formulate the symbolic regression problem as a mixed-integer nonlinear programming (MINLP) problem and use MINLP solvers to systematically solve multiple functional forms at once, instead of via the traditional approaches that use genetic algorithms. Future approaches to integrate symbolic regression with chemical theory will be discussed.

Tyler R. Josephson is an Assistant Professor in the Chemical, Biochemical, and Environmental Engineering department at the University of Maryland, Baltimore County. He received his B.S. in Chemical Engineering from the University of Minnesota in 2011, and his Ph.D. in Chemical Engineering from the University of Delaware in 2017, after which he was a postdoctoral associate in the University of Minnesota Chemistry Department. Prof. Josephson uses multi-scale modeling and machine learning to study catalysis, solvation, adsorption, and phase equilibria. During his downtime, he loves learning new things, thinking about deep topics (like science and philosophy), and playing the piano.

• Eligibility requirements for students include being a full-time UMBC student 12 hours undergraduate, 9 hours graduate), a minimum 2.75 cumulative GPA, and in good-academic standing. In addition, students must be connected to other student communities on campus (e.g. SGA, GSA, student organizations, scholar community members). If you are graduating within one year of your term, it is expected that you will continue in your role as a young alumni. 
• Eligibility requirements for staff and faculty include at least 1 full year of employment at the university.
• Eligibility Requirements for alumni must have been connected to alumni chapters or organizations (e.g. Alumni Board of Directors, CBLA, CYA) or student communities during their time on campus (e.g. SGA, GSA, student organizations, scholar community members) 

• Please provide a brief introduction that includes your three most salient social identities. Salient social identities are those that a person considers most important to their self-concept (e.g. race, ethnicity, religious identity/affiliation, gender, sexual orientation). If you need more examples or explanation, please visit: tinyurl.com/i3bidentitygroups.
• What is your past and/or present connection to i3b; the Mosaic, Interfaith, and Pride Centers; and/or diversity, equity, inclusion and social justice work broadly at UMBC?
• Why are you interested in joining the i3b Advisory Board? What skills, experiences, or expertise make you a good fit for this Board? What other relevant committees do you currently serve in?
• What do you hope to gain from being a member of the i3b Advisory Board?
• Share a short story about one of your earliest/most significant memories in coming to acknowledge and/or appreciate one or more of the salient identities you mentioned during your introduction? And how this personal journey allow you to better support diversity, inclusion, equity, and social justice work at UMBC.
• (Optional):Is there anything else that you would like us to know?

• Thursday, February 11th, 3pm - 4:30pm
• Thursday, February 25th, 3pm - 4:30pm
• Thursday, April 1st, 3pm - 4:30pm
• Thursday, May 6th, 3pm - 5pm