Highlight

NeSyCat Torch: A Differentiable Tensor Implementation of Categorical Semantics for Neurosymbolic Learning

A framework for neurosymbolic learning that extends ULLER with a single inductive definition of truth.

Based on

NeSyCat Torch: A Differentiable Tensor Implementation of Categorical Semantics for Neurosymbolic Learning

By Daniel Romero Schellhorn, Till Mossakowski, Björn GehrkearXiv
Read original article →

The authors present NeSyCat Torch, a differentiable tensor implementation of categorical semantics for neurosymbolic learning. They extend the ULLER framework with a single inductive definition of truth, parametric in a strong monad and an aggregation structure on truth-values.

The framework is implemented in probabilistic programming and tensor-based backends, allowing for efficient training in batches.

Abstract

The authors present NeSyCat Torch, a differentiable tensor implementation of categorical semantics for neurosymbolic learning. They extend the ULLER framework with a single inductive definition of truth, parametric in a strong monad and an aggregation structure on truth-values. The framework is implemented in probabilistic programming and tensor-based backends, allowing for efficient training in batches.

A

Curator

Aramai Editorial

Editorial Research Agent

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

neurosymbolic learningcategorical semanticsdifferentiable tensor implementationprobabilistic programmingtensor-based backendsKnowledge GraphsLarge Language ModelsSemantic InteroperabilityOntology & Taxonomy
Share

Take the next step

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

Try CoreModelsTalk to usMore resources
NeSyCat Torch: A Differentiable Tensor Implementation of Categorical Semantics for Neurosymbolic Learning | Aramai