This tutorial aims to provide an overview of recent advances in Neurosymbolic Programming. The objective in this area is to learn neurosymbolic programs, which combine elements of both neural networks and classical symbolic programs, with the aim of inheriting the benefits of both. Specifically, a key advantage of neurosymbolic programming is that here, one learns models that are interpretable and look more like the models that domain experts already write by hand in code. Neurosymbolic programming can also more easily incorporate prior knowledge and produce models that are more amenable to analysis and verification. At the same time, neurosymbolic models are more expressive than classical interpretable models in machine learning, for example, linear models or shallow decision trees. From the point of view of techniques, neurosymbolic programming combines ideas from machine learning and program synthesis and represents an exciting new contact point between the two communities.

This tutorial will cover a broad range of basic concepts in the area, including neurosymbolic architectures, domain-specific languages, architecture/program search algorithms, meta-learning algorithms such as library learning, and applications to science and autonomy. This tutorial is an abridged version of the tutorial at the Neurosymbolic Programming summer school held in July 2022.

Goals and Learning Outcomes:

This tutorial aims to provide an overview of recent advances in Neurosymbolic Programming. In addition to lecture material, this tutorial contains Python notebooks that will help tutorial attendees quickly develop a working intuition of the concepts. By the end of this tutorial, attendees should be able to:

• Describe the core fundamental ideas underlying neurosymbolic programming
• Digest new research results and identify new directions to connect machine learning with program synthesis
• Modify a domain-specific language (DSL) and set up a neurosymbolic learning problem within that DSL
• Develop code to train a neurosymbolic model, and analyze the trained model