Virtual talk summary: Data collection is ubiquitous…and not always benign. It can feel creepy to get online prompts about what to eat, watch, do, or buy. And biases in computer code can skew data-driven decisions in ways that negatively impact individuals without their knowledge. But there’s good news, too. Penn researchers are harnessing huge data […]

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 learn functions from data. However, these functions are represented as programs that use neural network modules as well as symbolic primitives and are induced using […]