Abstract: 

For decades, we have built software by writing code, but in recent years machine learning has emerged as a new approach to create software with features that would be impossible to code by hand. However, the use of learning to build software risks ignoring some of the lessons we have learned for how to build computer systems that are robust and maintainable. In this talk, I will describe a new class of techniques we have developed under the term “neurosymbolic programming” which aim to support learning while maintaining some of the benefits of traditional programming, such as modularity, interpretability, reusability and incremental development, and will show some of the benefits these techniques can offer in domains ranging from robotics to computational biology.

Zoom Link (if unable to attend in-person): https://upenn.zoom.us/j/93017587225