论文标题
通过神经网络使逻辑可学习
Making Logic Learnable With Neural Networks
论文作者
论文摘要
尽管神经网络擅长从培训样本中学习未指定的功能，但它们不能直接在硬件中实现，并且通常无法解释或正式验证。另一方面，逻辑电路是可实施的，可验证的和可解释的，但无法以可普遍的方式从培训数据中学习。我们提出了一种新型的逻辑学习管道，结合了神经网络和逻辑电路的优势。我们的管道首先在分类任务上训练神经网络，然后将其转换为随机森林，然后转换为逆变器逻辑。我们表明，我们的管道比天真的翻译对逻辑保持更高的准确性，并最大程度地减少逻辑，使其更容易解释并降低了硬件成本。我们在对生物医学数据培训的网络上显示了管道的实用性。该方法可以应用于患者护理，以提供风险分层并指导临床决策。
While neural networks are good at learning unspecified functions from training samples, they cannot be directly implemented in hardware and are often not interpretable or formally verifiable. On the other hand, logic circuits are implementable, verifiable, and interpretable but are not able to learn from training data in a generalizable way. We propose a novel logic learning pipeline that combines the advantages of neural networks and logic circuits. Our pipeline first trains a neural network on a classification task, and then translates this, first to random forests, and then to AND-Inverter logic. We show that our pipeline maintains greater accuracy than naive translations to logic, and minimizes the logic such that it is more interpretable and has decreased hardware cost. We show the utility of our pipeline on a network that is trained on biomedical data. This approach could be applied to patient care to provide risk stratification and guide clinical decision-making.
