DeepDFA: 在深度学习中注入时序逻辑用于序列子符号应用
DeepDFA: Injecting Temporal Logic in Deep Learning for Sequential Subsymbolic Applications
AI总结：
DeepDFA通过将时序逻辑整合到深度学习中，实现了在序列子符号应用中的高效知识注入和卓越性能。
摘要：
将逻辑知识整合到深度神经网络训练中仍然是一个严峻的挑战，尤其是在涉及子符号观察的顺序或时间扩展领域。为了解决这个问题，我们提出了DeepDFA，这是一种将高级时序逻辑——以确定有限自动机（DFA）或摩尔机的形式表达——整合到神经架构中的神经符号框架。DeepDFA将时序规则建模为连续、可微的层，使符号知识能够注入到子符号领域中。我们展示了DeepDFA在两个关键设置中的应用：（i）静态图像序列分类，以及（ii）在交互非马尔可夫环境中进行策略学习。在广泛的实验中，DeepDFA在传统深度学习模型（如LSTMs、GRUs、Transformers）和新型神经符号系统中均表现优异，实现了时序知识整合的最先进结果。这些结果突显了DeepDFA在顺序任务中连接子符号学习和符号推理的潜力。
英文摘要：
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.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
