DART Seed Grant Recipient Presentations, Session 2

Title: DART Seed Grant Recipient Presentations, Session 2Presenter(s): Yasir Rahmatallah, Jason Causey, Sudeep Bhattacharyya, and Melody GreerDate: October 26, 2022 Description This month’s webinar will feature three presentations from the recently awarded DART YR 3 Seed Grant Recipients. Yasir Rahmatallah (UAMS) will present on Machine Learning Approaches for Remote Pathological Speech Assessment for Parkinson’s Disease….Continue Reading DART Seed Grant Recipient Presentations, Session 2

DART Seed Grant Recipient Presentations, Session 1

Title: DART Seed Grant Recipient Presentations, Session 1Presenter(s): Xiao Huang and Ahmed Abu HalimehDate: September 28, 2022 Description This month’s webinar will feature two presentations from the recently awarded DART YR 3 Seed Grant Recipients. Dr. Xiao Huang (UAF)will present on AI-Supported Cyberinfrastructure for Scalable Flood Resilience Assessment. This project is part of the CI…Continue Reading DART Seed Grant Recipient Presentations, Session 1

Data Life Cycle and Curation Graduate Student Lightening Talks

Title: Data Life Cycle and Curation Graduate Student Lightening TalksPresenter(s): Jewel Banik, Journey Eubank, Ashley Herdman, Sangam Kandel, Kanishka Manna, Sudip Panday, and Dave UsseryDate: August 31, 2022 Description This month’s webinar will feature lightening talks from 6 graduate students working in the Data Life Cycle and Curation Research Theme at the University of Arkansas…Continue Reading Data Life Cycle and Curation Graduate Student Lightening Talks

2+2 Program Work-in-Progress

Title: 2+2 Program Work-in-progress, presented by the Education RTPresenter(s): Education RTDate: April 27, 2022 Description A major element of our Education Research Theme is to create pathways for Data Science students from 2-year colleges through A.S. degrees and certificates and then to 4-year colleges and universities for completion of a B.S. in Data Science in…Continue Reading 2+2 Program Work-in-Progress

Racial and Gender Homophily in Classroom Discussion Networks

Title: Racial and Gender Homophily in Classroom Discussion NetworksPresenter(s): Regan Harper (UAF DART GRA)Date: March 30, 2022 Description Previous studies on homophily tend to focus on positive social relationships, like friendships, which overlooks the negative networks formed through the access to internet. Our study employs an online discussion platform and examines the hidden and invisible…Continue Reading Racial and Gender Homophily in Classroom Discussion Networks

Prediction and learning for designing materials for solar energy conversion

Title: Prediction and learning for designing materials for solar energy conversionPresenter(s): Rob CoridanDate: February 23, 2022 Description Materials for converting solar energy into chemical fuels requires balancing the many physical and chemical steps involved (light absorption, catalysis, product separation, diffusion of reactants and products) along multiple length scales (from single atoms to m2). This balance…Continue Reading Prediction and learning for designing materials for solar energy conversion

Precognition: Seeing through the Future

Title: Precognition: Seeing through the Future Presenter(s): Khoa Luu Date: January 26, 2022 Description Vision-based detection and recognition studies have been recently achieving highly accurate performance and were able to bridge the gap between research and real-world applications. Beyond these well-explored detection and recognition capabilities of modern algorithms, vision-based forecasting will likely be one of the next…Continue Reading Precognition: Seeing through the Future

Deep Learning in Biomedical Imaging

Title: Deep Learning in Biomedical Imaging Presenter(s): Ngan Le Date: December 1, 2021 Description Medical image analysis using deep learning has recently been prevalent, showing great performance for various downstream tasks including medical image segmentation and its sibling, volumetric image segmentation. Particularly, a typical volumetric segmentation network strongly relies on a voxel grid representation which…Continue Reading Deep Learning in Biomedical Imaging

Data Science Student Lightening Talks

Title: Data Science Student Lightening Talks Presenter(s): Trace Freeman, Jacob Haarala, Hayden McDonald, Lydia Sloan, Benjamin Zamzow, and Karl Schubert Date: November 17, 2021 Description During this webinar we will hear from five of data science students working in the Education Research Theme. Overview Discussion, presented by Dr. Karl Schubert Course Equivalency Project, presented by…Continue Reading Data Science Student Lightening Talks

Towards Robust Machine Learning under Distribution Shift and Adversarial Attack

October 27, 2021 (Xintao Wu)

As big data and AI technologies are deployed to make critical decisions that potentially affect individuals (e.g., employment, college admissions, credit, and health insurance), there are increasing concerns from the public on privacy, fairness, safety, and robustness issues of data analytics, collection, sharing and decision making. In this talk, we first overview our social awareness research, in particular, on how to mitigate side effect of enforcing one social concern on another, and how to address multiple social concerns simultaneously. We then focus on robustness of machine learning under two representative scenarios, distribution shift and adversarial attack. In the former scenario, we present robust learning based on kernel reweighing and Heckman model. In the second scenario, we present adaptive defense that purposely leverages multiple types of adversarial samples to learn the context information in the training. We conclude the talk with some future research directions….Continue Reading Towards Robust Machine Learning under Distribution Shift and Adversarial Attack