At the Center for Data Science, we strive to facilitate the highest quality data science research, education, and industry collaboration. We work closely with industry partners on projects addressing their business needs, and we are educating the next generation of data science professionals.
Octavia Eugen Ganea (CSAIL-MIT): Hyperbolic Geometry in Machine Learning
Machine Learning and Friends Lunch
February 13, 12:00pm to 1:00pm
Computer Science Building, Room 150/151
I will discuss some of the recent advances in using non-Euclidean geometry in machine learning, mostly focusing on hyperbolic geometry. After introducing some important concepts such as curvature, I will discuss how hyperbolic embeddings can be used to model entailment or hypernymy relations. Next, I will present extensions of basic deep learning architectures to hyperbolic spaces, showcasing how this geometry can be leveraged in standard ML pipelines.
Industry Mentorship Team Presents Paper at NLP Conference
In a paper presented at the 2019 Conference on Empirical Methods in Natural Language Processing (EMNLP), Master’s student Kriti Myer, along with Master’s students Pallavi Patil, Ronak Zala, and Arpit Singh, doctoral student Sheshera Mysore, Distinguished Professor Andrew McCallum, and industry mentors Adrian Benton and Amanda Stent from Bloomberg, described a new approach to predicting how a member of Congress will vote on a bill, using information about the member from news articles and Freebase, a manually curated knowledge base.