用有限状态机增强神经网络，让模型学会时间逻辑规则。
DeepDFA: Injecting Temporal Logic in Deep Learning for Sequential Subsymbolic Applications
- 将时序逻辑转为可微分层，嵌入神经网络
- 在序列分类与非马尔可夫环境中表现超越主流模型
- 适合需要时间推理的智能系统开发
将逻辑知识融入深度神经网络训练仍是难题，尤其在涉及子符号观测的时序或延展域。为此，我们提出 DeepDFA，一个神经符号框架，将高层时序逻辑（以确定性有限自动机 DFA 或莫尔机形式表达）融入神经架构。DeepDFA 将时序规则建模为连续可微层，实现符号知识对子符号领域的注入。我们在两个关键场景中验证其有效性：(i) 静态图像序列分类，(ii) 交互式非马尔可夫环境中的策略学习。大量实验表明，DeepDFA 在时序知识融合方面优于传统深度学习模型（如 LSTMs、GRUs、Transformers）和新型神经符号系统，达到该任务的最先进水平。结果凸显了 DeepDFA 在连接子符号学习与符号推理方面的潜力。
原文摘要 · Abstract (English)
Integrating logical knowledge into deep neural network training is still a hard challenge, especially for sequential or temporally extended domains involving subsymbolic observations. To address this problem, we propose DeepDFA, a neurosymbolic framework that integrates high-level temporal logic - expressed as Deterministic Finite Automata (DFA) or Moore Machines - into neural architectures. DeepDFA models temporal rules as continuous, differentiable layers, enabling symbolic knowledge injection into subsymbolic domains. We demonstrate how DeepDFA can be used in two key settings: (i) static image sequence classification, and (ii) policy learning in interactive non-Markovian environments. Across extensive experiments, DeepDFA outperforms traditional deep learning models (e.g., LSTMs, GRUs, Transformers) and novel neuro-symbolic systems, achieving state-of-the-art results in temporal knowledge integration. These results highlight the potential of DeepDFA to bridge subsymbolic learning and symbolic reasoning in sequential tasks.
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。