基于语法指导的机器学习模型的可能近似正确表示
Probably Approximately Correct Explanations of Machine Learning Models via Syntax-Guided Synthesis
摘要:
我们提出了一种新的方法来理解复杂机器学习模型的决策(例如,深度神经网络)使用可能近似正确学习(PAC)和被称为语法引导合成(SyGuS)的逻辑推理方法的组合。我们证明,我们的框架产生的解释很有可能只产生很少的错误,并根据经验表明,它可以有效地产生小的、人类可解释的解释。
英文摘要:
We propose a novel approach to understanding the decision making of complex machine learning models (e.g., deep neural networks) using a combination of probably approximately correct learning (PAC) and a logic inference methodology called syntax-guided synthesis (SyGuS). We prove that our framework produces explanations that with a high probability make only few errors and show empirically that it is effective in generating small, human-interpretable explanations.
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。