Title: Deconstructing models and methods in deep learning
Abstract: Machine learning models are ultimately used to make decisions in the real world, where mistakes can be incredibly costly. We still understand...
Title: Deconstructing models and methods in deep learning
Abstract: Machine learning models are ultimately used to make decisions in the real world, where mistakes can be incredibly costly. We still understand...
Fair registration for students will open on Wednesday, February 8th (two weeks prior to the fair). If you would like to receive an alert when registration opens, please favorite the fair and Handshake will alert you when...
Title: (Un)trustworthy Machine Learning: How to Balance Security, Accuracy, and Privacy
Abstract: Machine learning methods have become a commodity in the toolkits of both researchers and practitioners. For...
Title: Collaborative, Communal, & Continual Machine Learning
Abstract: Pre-trained models have become a cornerstone of machine learning thanks to the fact that they can provide improved performance with...
Fair registration for students will open on Wednesday, February 8th (two weeks prior to the first day of the fair). If you would like to receive an alert when registration opens, please favorite the fair and Handshake...
Title: A new approach for simulating randomness in computation, and resulting directions of research
Abstract: Randomness is used throughout computer science, but when does it actually make computation more...
Matrices are ubiquitous mathematical structures arising throughout computer science. We study fast algorithms for several central problems involving matrices, including eigenvalue approximation, spectral approximation,...
Abstract: TBA
Bio: TBA
The Systems Lunch talk series organized by Emery Berger is back in person! All talks are Fridays at 12:00 pm Eastern in room A311 (LGRC). Systems Lunch is a great opportunity to hear...
HackHer413 is the first all-women (cis and trans) and non-binary student hackathon in Western Massachusetts. This hackathon is a 24-hour technology marathon where participants form teams to collaborate in creating unique...
Abstract: Graphs are ubiquitous data structures, present in many machine-learning tasks, such as link prediction, node classification, ontology alignment, etc. As gradient descent drives the training of most modern...