将ASP与能量模型结合，实现可端到端训练的神经符号推理。
Answer Set Programming Energised! End-to-End Neurosymbolic Reasoning and Learning with ASP and Energy Based Models
- 用ASP构建可解释的逻辑框架，支持带背景知识的联合优化。
- 在Clevr和MOT上实现端到端训练，准确率优于传统方法。
- 适合需要可解释性推理的动态感知任务场景。
我们提出一种基于答案集编程（ASP）与能量基模型融合的通用神经符号推理与学习方法。核心贡献包括：(1) 通过显式的ASP声明式语义，在连续潜空间中实现联合优化，完整融入背景知识、约束及非单调推理；(2) 在答案集、概率逻辑与答案集模理论交叉领域推进现有工作，提供适用于以ASP为中心的鲁棒端到端训练的通用模型与实用平台，适用于涉及感知与交互的动态领域。我们实现了该方法，并在MNIST上展示基础应用，进一步在视觉问答基准Clevr与多目标跟踪基准MOT上进行评估。
原文摘要 · Abstract (English)
We present a general neurosymbolic reasoning and learning methodology based on a modular integration of answer set programming with an energy based model substrate. Key contributions are: (1) supporting joint optimisation in the continuous latent space through explicit ASP-based declarative semantics fully incorporating background knowledge, constraints, non-monotonic inference; and (2) advancing recent works at the interface of answer sets, probabilistic logic, and answer set modulo theories by providing a generalised model and practical platform for ASP-centric robust, end-to-end training for applications in dynamic domains (e.g., involving perception and interaction). We provide a practical implementation, and demonstrate basic use and application (with MNIST), and evaluate with the visual question-answering benchmark Clevr and the multi-object tracking benchmark MOT.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。