# Composing Neural Learning and Symbolic Reasoning with an Application to Visual Discrimination

arXiv: https://arxiv.org/abs/1907.05878 · HTML: https://mlsanity.com/paper/1907.05878/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 12 Jul 2019.

## Built on by (most cited first, 4 of 4)

- [PuzzlePlex: Benchmarking Foundation Models on Reasoning and Planning with Puzzles](https://mlsanity.com/paper/2510.06475/) (2025)
- [Rapid Image Labeling via Neuro-Symbolic Learning](https://mlsanity.com/paper/2306.10490/) (2023)
- [SYNAPSE: SYmbolic Neural-Aided Preference Synthesis Engine](https://mlsanity.com/paper/2403.16689/) (2024)
- [Agents as Software: A Programming Languages Agenda for Agent Reliability](https://mlsanity.com/paper/2609.32198/) (2026)

## Abstract (arXiv)

We consider the problem of combining machine learning models to perform higher-level cognitive tasks with clear specifications. We propose the novel problem of Visual Discrimination Puzzles (VDP) that requires finding interpretable discriminators that classify images according to a logical specification. Humans can solve these puzzles with ease and they give robust, verifiable, and interpretable discriminators as answers. We propose a compositional neurosymbolic framework that combines a neural network to detect objects and relationships with a symbolic learner that finds interpretable discriminators. We create large classes of VDP datasets involving natural and artificial images and show that our neurosymbolic framework performs favorably compared to several purely neural approaches.