Final Program [Download PDF] [Download Abstracts] [Download Speaker Bio]
See slides and posters here: AIDR Collection @ F1000Research
Selected papers now published @ ACM Digital Library: AIDR '19 Proceedings - ACM ICPS
------------------
----------------------
-----------------------
-----------------------
Monday, May 13
Time | Session | Speaker | Title |
---|---|---|---|
8:00 -- 9:00 | Breakfast | ||
9:00 -- 9:15 | Welcome and Opening Remarks |
Keith Webster, Dean, CMU Libraries Michael McQuade, Vice President for Research, CMU Beth Plale, CISE/OAC, NSF |
|
9:15 -- 10:15 | Keynote 1 | Tom Mitchell, Carnegie Mellon University | Discovery from Brain Image Data |
10:15 -- 10:35 | Break | ||
10:35 -- 12:20 | Session 1: Automation in data curation and metadata generation (Chair: Paola Buitrago) | ||
Long Talk | Cornelia Caragea, University of Illinois at Chicago | Keyphrase extraction from scholarly documents for data discovery and reuse | |
Long Talk | Natasa Miskov-Zivanov, University of Pittsburgh | Dynamic System Explanation, DySE, a framework that evolves to reason about complex systems. | |
Short Talk | Matias Carrasco Kind, National Center for Supercomputing Applications (NCSA) | Searching for similarities and anomalies in a pool of galaxy images using Deep Learning | |
Short Talk | Rema Padman, Carnegie Mellon University | Ask the Doctor if YouTube is Right for You: An Augmented-Intelligence Video Recommender System for Patient Education | |
Short Talk | Claudia Engel, Stanford University | Image Recognition for Archaeological Research | |
12:20 --13:20 | Lunch | ||
13:20 -- 15:05 | Session 2: Automation in data discovery (Chair: Huajin Wang) | ||
13:20 -- 13:50 | Invited Talk | Natasha Noy, Google AI | Google Dataset Search: An open ecosystem for data discovery |
Short Talk | Fernando Chirigati, NYU | A Dataset Search Engine for Data Augmentation | |
Short Talk | Alexander New, Rensselaer Polytechnic Institute | A Semantalytic Approach to Accelerated Data Reuse for Reproducible Scientific Discovery | |
Short Talk | Shenghui Wang, OCLC Research, Netherlands | An innovative approach to scalable semantic search | |
Short Talk | Cornelia Caragea, University of Illinois at Chicago | Building Specialized Collections from Web Archiving | |
Short Talk | Jian Wu, Old Dominion University | Reuse and Discovery for Scholarly Big Data | |
15:05 -- 15:25 | Break | ||
15:25 -- 16:10 | Panel 1 | Keith Webster, Carnegie Mellon University (Moderator) Cliff Lynch, Coalition for Networked Information Natasha Noy, Google AI Casey Greene, University of Pennsylvania Alex London, Carnegie Mellon University Nick Nystrom, Pittsburgh Supercomputing Center |
Challenges and opportunities in data reuse using the power of AI |
16:10 -- 17:30 | Poster + Networking | ||
17:30 -- 19:30 | Reception |
Tuesday, May 14
Time | Session | Speaker | Title |
---|---|---|---|
8:00 -- 9:00 | Breakfast | ||
9:00 -- 10:00 | Keynote 2 | Glen de Vries, Medidata Solutions | Clinical trials in the age of AI and Precision Medicine |
10:00 --10:20 | Break | ||
10:20 -- 12:05 | Session 3: Integrating datasets and enabling interoperability (Chair: Nick Nystrom) | ||
Short Talk | Evgeny Toropov, Carnegie Mellon University | Data reuse through domain adaptation AI algorithms for the self driving industry | |
Long Talk | Jiacheng Zhu, Carnegie Mellon University | A self-organized Scenario-based Heterogeneous Traffic Database for Autonomous Vehicles | |
Short Talk | Daniel Clothiaux, Carnegie Mellon University | Visual and Statistical Analysis and Comparison of Handwritten and Font Datasets | |
Short Talk | Xu Fei, Code Ocean | Lowering the barriers to experiment, data, and method reproducibility in AI research with a cloud-based computational reproducibility platform | |
Short Talk | Rémi Mégret, University of Puerto Rico, Rio Piedras campus | LabelBee: a web platform for large-scale semi-automated analysis of honeybee behavior from video | |
12:05 -- 13:00 | Lunch | ||
13:00 -- 17:00 | Session 4: Biomedical applications (Chairs: Sean Davis and Andreas Pfenning) | ||
13:00 -- 13:30 | Invited Talk | Casey Greene, University of Pennsylvania | Data reuse enables ML-based analysis of rare diseases |
13:30 -- 13:45 | Short Talk | Ben Busby, NCBI | Prototype ML Software for Several Distinct Classes of Biomedical Data Science Problems Developed in NIH-Hackathons! |
13:45 -- 14:15 | Invited Talk | Lisa S. Parker, University of Pittsburgh | Data Privacy: Control, Use, and Governance |
14:15 --14:30 | Break | ||
14:30 -- 15:00 | Invited Talk | Sean Davis, National Cancer Institute, NIH | Data engineering: tools and approaches to facilitate data reuse and data science |
15:00 -- 15:15 | Invited Short Talk | Irene Kaplow, Carnegie Mellon University | Predicting Tissue-Specific cis-Regulatory Elements Across Mammals to Identify Potential Evolutionary Mechanisms |
15:15 -- 15:45 | Invited Talk | Fiona Nielsen, Repositive | Standards, incentives, tools – Which are the necessities for data discovery in academia vs industry? |
15:45 -- 16:00 | Break | ||
16:00 -- 16:30 | Invited Talk | Alex London, Carnegie Mellon University | Understanding the Role of Explainaiblity and Verification in Medical AI |
16:30 -- 16:45 | Invited Short Talk | Nick Nystrom, PSC and Carnegie Mellon University | Enabling Data Discoverability in the Human BioMolecular Atlas Program (HuBMAP) |
16:45 -- 17:15 | Invited Talk | Bob Murphy, Carnegie Mellon University | AI for Biological Discovery: Data Integration and Self-Driving Instruments |
17:15 | Dinner on your own |
Wednesday, May 15
Time | Session | Speaker | Title |
---|---|---|---|
8:00 -- 8:45 | Breakfast | ||
8:45 -- 9:30 | Outcome and future planning meeting - all invited to participate (Moderator: Huajin Wang) | ||
9:30 -- 10:15 | Panel 2 | Karen Lightman, Metro21: Smart Cities Institute (Moderator) Robet Tamburo, Carnegie Mellon University Bob Gradeck, Western Pennsylvania Regional Data Center Santi Garces, City of Pittsburgh |
Enabling Smart and Safe Communities Through AI |
10:15 -- 10:35 | Break | ||
10:35 -- 11:55 | Session 5: Data security, privacy and algorithmic bias | ||
Invited Talk | Matt Fredrikson, Carnegie Mellon University | Finding Bias, Discrimination, and Private Data Leakage in Machine Learning Systems | |
Long Talk | Lena Pons, Carnegie Mellon University | Sharable Cyber Threat Intelligence Using Weak Anonymization | |
Short Talk | Andrew Yale, Rensselaer Polytechnic Institute | Privacy Preserving Synthetic Health Data | |
Short Talk | Michael Ellis, University of North Carolina at Greensboro | Protecting fMRI data from unforeseen privacy attacks in a distributed machine learning environment | |
11:55 -- 12:10 | Closing remarks | Keith Webster, Carnegie Mellon University | |
12:10 | Ajourn. Boxed lunch to go |
Post-conference event
Software Engineering Institute (SEI) Research Services High Tea 2019
Time: 14:00
Location: Jordan Auditorium
Speaker | Title |
---|---|
Tom Longstaff, SEI Chief Technical Officer (Mater of Ceremonies) | |
Keith Webster, Dean of Carnegie Mellon University Libraries | The Library’s Role in the Fourth Industrial Revolution |
Sarah Sheard, Principal engineer, Software Engineering Institute, Carnegie Mellon University | Systems at the SEI |
Matt Burton, Lecturer, School of Computing and Information, University of Pittsburgh | AI and the Future of Library Science |
Tom Corbett, Special Faculty, Entertainment Technology Center, Carnegie Mellon University | Forms Follow Functions: How AI and Spatial Computing Will Impact the Future of Video Games and Historic Preservation |
English high tea reception
Time: 15:00
Location: SEIber Café