Office of Undergraduate Research

Permanent URI for this communityhttp://hdl.handle.net/1903/20157

Emphasizing equitable and inclusive access to research opportunities, the University of Maryland's Office of Undergraduate Research (OUR) empowers undergraduates and faculty to engage and succeed in inquiry, creative activity, and scholarship. This collection includes materials shared by undergraduate researchers during OUR events. It also encompasses materials from Undergraduate Research Day 2020, Undergraduate Research Day 2021, and Undergraduate Research Day 2022, which were organized by the Maryland Center for Undergraduate Research.

Browse

Subject: search.filters.subject.Deep Learning

Search Results

Now showing 1 - 2 of 2
  • Thumbnail Image
    Item
    Interpretable Deep Learning for Toxicity Prediction
    (2020) Banerjee, Aranya; Boby, Kevin; Lam, Samuel; Li, Jeffrey; Polefrone, David; San, Robert; Schlunk, Erika; Wynn, Sean; Yancey, Colin; Feizi, Soheil
    Team TOXIC (“Understanding Computational Toxicology”) seeks to apply interpretability techniques to machine learning models which predict drug safety. Currently, such models have been developed with relative accuracy and are used in industry for drug development. However, because they are not sufficiently rooted in chemical knowledge, they are not widely used in regulatory processes. To contribute towards a solution, we evaluate existing explanation methods for toxicity predction models trained on open-source data sets. Additionally, we are working towards models involving the usage of more interpretable data representations. Ultimately, we hope to demonstrate a proof-of-concept for an interpretable model for predicting drug safety which can illustrate its reasoning.
  • Thumbnail Image
    Item
    Balancing Fairness and Profit in Rideshare using Deep Learning
    (2020-04-26) Raman, Naveen; Dickerson, John
    Rideshare services such as Uber and Lyft have become much more popular over the last few years. Determining which riders are allocated to which drivers is a challenging problem, complicated by the number of combinations of riders and drivers. Current solutions typically optimize for gross mean volume or profit, while ignoring fairness in driver pay and rider wait-time. We address these by taking a long-term view, using Neural Networks to simulate value functions, and use Markov Decision Processes to maximize fairness.