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

• URL: http://arxiv.org/abs/2606.19279v1
• Date: Wed, 17 Jun 2026 16:56:31 GMT
• Title: NeSyCat Torch: A Differentiable Tensor Implementation of Categorical Semantics for Neurosymbolic Learning
• Abstract summary: NeSyCat subsumes truth under a single inductive definition of truth, parametric in a strong monad and an aggregation structure on truth-values.<n>We provide NeSyCat Torch as the missing link and interpret computational symbols via neural networks.
• Score: 0.0
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Neurosymbolic semantics is fragmented: classical, fuzzy, probabilistic and neural systems each define truth by their own inductive rules. NeSyCat, extending ULLER, subsumes them under a single inductive definition of truth, parametric in a strong monad and an aggregation structure on truth-values. NeSyCat has so far lacked an account of predicates and functions learned by neural networks. We provide NeSyCat Torch as the missing link and interpret computational symbols via neural networks, implementing the framework in probabilistic programming and tensor-based backends. We use the distribution monad for reference semantics and metric evaluation, and complement it by a monad for numerically stable, differentiable training: the lazy log-tensor monad over the log-semiring. For efficient training in batches, we furthermore employ a batch monad. The axioms are the source code: written once in monad-based do-notation, monadic bind performs marginalisation, lazily pruning unneeded branches. On MNIST addition, our HaskTorch, JAX, and PyTorch implementations outperform LTN and DeepProbLog in speed and accuracy, while achieving nearly the accuracy of DeepStochLog. However, unlike DeepStochLog, we stay in a uniform framework that applies to many first-order NeSy approaches. Namely, the construction is parametric in the monad; instantiating it with, e.g., the Giry monad extends the approach to continuous probability (working out a neural representation here is left for future work).

Related papers

• NeSyCat: A Monad-Based Categorical Semantics of the Neurosymbolic ULLER Framework [0.0]
  ULLER (Unified Language for LEarning and Reasoning) offers a unified first-order logic (FOL) syntax.<n>The original specification endows this syntax with three pairwise independent semantics: classical, fuzzy, and probabilistic.<n>We show that these seemingly disparate semantics are all instances of one categorical framework based on monads.
  arXiv  Detail & Related papers  (2026-04-27T15:40:15Z)
• Bearing Syntactic Fruit with Stack-Augmented Neural Networks [59.49467149799849]
  We show that stack-augmented neural networks are more accurate models of human language acquisition than standard architectures.<n>We also propose a modification to the stack RNN architecture that improves hierarchical generalization.
  arXiv  Detail & Related papers  (2025-11-05T15:30:58Z)
• v-PuNNs: van der Put Neural Networks for Transparent Ultrametric Representation Learning [0.0]
  We introduce van der Put Neural Networks (v-PuNNs), the first architecture whose neurons are characteristic functions of p-adic balls in $mathbbZ_p$.<n>Under our Transparent Ultrametric Representation Learning (TURL) principle every weight is itself a p-adic number, giving exact subtree semantics.<n>V-PuNNs therefore bridge number theory and deep learning, offering exact, interpretable, and efficient models for hierarchical data.
  arXiv  Detail & Related papers  (2025-08-01T18:23:38Z)
• Training Neural Networks as Recognizers of Formal Languages [87.06906286950438]
  We train and evaluate neural networks directly as binary classifiers of strings.<n>We provide results on a variety of languages across the Chomsky hierarchy for three neural architectures.<n>Our contributions will facilitate theoretically sound empirical testing of language recognition claims in future work.
  arXiv  Detail & Related papers  (2024-11-11T16:33:25Z)
• Scale Equivariant Graph Metanetworks [20.445135424921908]
  This paper pertains to an emerging machine learning paradigm: learning functions whose inputs are functions themselves. We propose $textitScale Equivariant Graph MetaNetworks - ScaleGMNs$, a framework that adapts the Graph Metanetwork (message-passing) paradigm by incorporating scaling symmetries.
  arXiv  Detail & Related papers  (2024-06-15T16:41:04Z)
• LINC: A Neurosymbolic Approach for Logical Reasoning by Combining Language Models with First-Order Logic Provers [60.009969929857704]
  Logical reasoning is an important task for artificial intelligence with potential impacts on science, mathematics, and society. In this work, we reformulating such tasks as modular neurosymbolic programming, which we call LINC. We observe significant performance gains on FOLIO and a balanced subset of ProofWriter for three different models in nearly all experimental conditions we evaluate.
  arXiv  Detail & Related papers  (2023-10-23T17:58:40Z)
• Equivariance with Learned Canonicalization Functions [77.32483958400282]
  We show that learning a small neural network to perform canonicalization is better than using predefineds. Our experiments show that learning the canonicalization function is competitive with existing techniques for learning equivariant functions across many tasks.
  arXiv  Detail & Related papers  (2022-11-11T21:58:15Z)
• Constrained Training of Neural Networks via Theorem Proving [0.2578242050187029]
  We formalise a deep embedding of linear temporal logic over finite traces (LTL$_f$) We then formalise a loss function $mathcalL$ that we formally prove to be sound, and differentiable to a function $dmathcalL$. We show that, when used for training in an existing deep learning framework for dynamic movement, our approach produces expected results for common movement specification patterns.
  arXiv  Detail & Related papers  (2022-07-08T13:13:51Z)
• Dynamic Inference with Neural Interpreters [72.90231306252007]
  We present Neural Interpreters, an architecture that factorizes inference in a self-attention network as a system of modules. inputs to the model are routed through a sequence of functions in a way that is end-to-end learned. We show that Neural Interpreters perform on par with the vision transformer using fewer parameters, while being transferrable to a new task in a sample efficient manner.
  arXiv  Detail & Related papers  (2021-10-12T23:22:45Z)
• On Lipschitz Regularization of Convolutional Layers using Toeplitz Matrix Theory [77.18089185140767]
  Lipschitz regularity is established as a key property of modern deep learning. computing the exact value of the Lipschitz constant of a neural network is known to be NP-hard. We introduce a new upper bound for convolutional layers that is both tight and easy to compute.
  arXiv  Detail & Related papers  (2020-06-15T13:23:34Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.