PulseAugur
实时 14:20:07
English(EN) A homotopy-type-theoretic generalization of neurosymbolic inference

新框架将神经符号学习与神经网络统一起来 · 跟踪2个来源

研究人员开发了 NeSyCat Torch,一个将范畴语义与神经网络相结合用于神经符号学习的新框架。该实现可在 HaskTorchJAXPyTorch 中使用,旨在通过提供单一的归纳真理定义来统一碎片化的语义系统。该系统在 MNIST 数据集上表现强劲,在速度和准确性方面均优于现有方法,同时保持了适用于各种神经符号方法的统一框架。 AI

影响 这项研究可能带来更统一、更高效的神经符号人工智能系统,从而可能提高需要逻辑推理和模式识别的任务的性能。

排序理由 该集群包含两篇 arXiv 论文,详细介绍了神经符号学习的新研究。

在 arXiv cs.AI 阅读 →

AI 生成摘要 · Google Gemini · 来自 4 个来源。 我们如何撰写摘要 →

新框架将神经符号学习与神经网络统一起来 · 跟踪2个来源

报道来源 [4]

  1. arXiv cs.AI TIER_1 English(EN) · Daniel Romero Schellhorn, Till Mossakowski, Bj\"orn Gehrke ·

    NeSyCat Torch: 神经符号学习的范畴语义可微分张量实现

    arXiv:2606.19279v1 Announce Type: new 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, parametr…

  2. arXiv cs.AI TIER_1 English(EN) · Björn Gehrke ·

    NeSyCat Torch: 神经符号学习的分类语义可微分张量实现

    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 structur…

  3. arXiv cs.AI TIER_1 English(EN) · Fernando Zhapa-Camacho, Robert Hoehndorf ·

    神经符号推理的同伦类型论推广

    arXiv:2606.17851v1 Announce Type: new Abstract: A wide range of neurosymbolic (NeSy) systems compute one functional: a belief-weighted sum of a logical quantity over a space of $\sigma$-structures, of which weighted model counting, fuzzy logic, and probabilistic logic are special…

  4. arXiv cs.AI TIER_1 English(EN) · Robert Hoehndorf ·

    神经符号推理的同伦类型论推广

    A wide range of neurosymbolic (NeSy) systems compute one functional: a belief-weighted sum of a logical quantity over a space of $σ$-structures, of which weighted model counting, fuzzy logic, and probabilistic logic are special cases. This account is built on sets, and a set deli…