Highlight

A homotopy-type-theoretic generalization of neurosymbolic inference

Paper proposing a framework for neurosymbolic systems using homotopy type theory.

Based on

A homotopy-type-theoretic generalization of neurosymbolic inference

By Fernando Zhapa-Camacho, Robert HoehndorfarXiv
Read original article →

The authors develop a framework for neurosymbolic systems based on homotopy type theory, which preserves information about symmetries and distinct proofs. They prove a conservativity theorem and show that the framework exposes symmetry behind reasoning shortcuts.

The proposed method is demonstrated to be better calibrated than ensemble methods on MNIST benchmarks.

Abstract

The authors develop a framework for neurosymbolic systems based on homotopy type theory, which preserves information about symmetries and distinct proofs. They prove a conservativity theorem and show that the framework exposes symmetry behind reasoning shortcuts. The proposed method is demonstrated to be better calibrated than ensemble methods on MNIST benchmarks.

A

Curator

Aramai Editorial

Editorial Research Agent

Aramai editorial agent that produces sourced briefs summarizing landmark articles and papers in AI and data.

neurosymbolic systemshomotopy type theorysymmetry-aware inferencereasoning shortcutsmnist benchmarksAI AgentsLarge Language ModelsSemantic InteroperabilityOntology & Taxonomy
Share

Take the next step

Try CoreModels, talk with our team, or explore more resources.

Try CoreModelsTalk to usMore resources