Neurosymbolic Programming

Abstract

We survey recent work on neurosymbolic programming, an emerging area that bridges the areas of deep learning and program synthesis. Like in classic machine learning, the goal here is to learn functions from data. However, these functions are represented as programs that can use neural modules in addition to symbolic primitives and are induced using a combination of symbolic search and gradient-based optimization. Neurosymbolic programming can offer multiple advantages over end-to-end deep learning. Programs can sometimes naturally represent long-horizon, procedural tasks that are difficult to perform using deep networks. Neurosymbolic representations are also, commonly, easier to interpret and formally verify than neural networks. The restrictions of a programming language can serve as a form of regularization and lead to more generalizable and data-efficient Swarat Chaudhuri, Kevin Ellis, Oleksandr Polozov, Rishabh Singh, Armando SolarLezama and Yisong Yue (2021), “Neurosymbolic Programming”, Foundations and Trends® in Programming Languages: Vol. 7, No. 3, pp 158–243. DOI: 10.1561/2500000049. ©2021 S. Chaudhuri et al. The version of record is available at: http://dx.doi.org/10.1561/2500000049