Pre-trained models have become a cornerstone of machine learning thanks to the fact that they can provide improved performance with less labeled data on downstream tasks. However, these models are […]
Please join Ruzena Bajcsy, Susan Davidson, Stephanie Weirich and Linh Phan for a panel discussion. Reception to Follow ABSTRACT: Women have always been part of computing at Penn, from the […]
ABSTRACT: An important goal of the field sensorimotor robot learning is to do away with cumbersome expertise-intensive task specification, so that general-purpose robots of the future might learn large numbers […]
ABSTRACT: Many regression and classification procedures fit a function f(x;w) of predictor variables x to data 〖{x_i,y_i}〗_1^N based on some loss criterion L(y,f(x;w)). Often, regularization is applied to improve accuracy […]
ABSTRACT: The training data that modern machine learning models ingest has a major impact on these models’ performance (as well as failures). Yet, this impact tends to be neither fully […]
PRESENTATION ABSTRACT: In this new era of deep learning, the emergent algorithmic reasoning capabilities of Transformer models have led to significant advancements in natural language processing, program synthesis, and theorem […]
Abstract: Scientific discoveries, fueled by data collected during the course of care, are promising to radically change how we think about health, disease, prevention and treatment. However, the very systems […]
ABSTRACTION IN LANGUAGES AND SYSTEMS Laureate symposium honoring Barbara Liskov, recipient of the 2023 Benjamin Franklin Medal in Computer and Cognitive Science Featuring: Barbara Liskov, Ph.D., Laureate […]
PRESENTATION ABSTRACT: Neurosymbolic programming (NSP) is an emerging area of computing that bridges the fields of deep learning and program synthesis. Like in classical machine learning, the goal here is to […]
