NBDT：神經支援決策樹

• 2020 年 4 月 3 日
• 筆記

深度學習正被用於那些要求準確且合理預測的領域中，例如金融和醫學成像。雖然最近的研究對模型預測做了因果解釋，但很少有研究探究能直接解釋的模型，以匹配最先進的精確度。在過去，決策樹一直是平衡解釋性和精確度的黃金標準。然而，最近人們試圖將決策樹和深度學習結合起來，得出了一些模型。這些模型（1）的精確度比現代神經網路要低得多（例如：殘差網路ResNet），即使是在小數據集中（例如：MNIST）。而且，這些模型還（2）需要各種不同的系統構架，這使得操作人員不得不在精確性和解釋性中做選擇。

原文標題：NBDT: Neural-Backed Decision Trees

原文：Deep learning is being adopted in settings where accurate and justifiable predictions are required, ranging from finance to medical imaging. While there has been recent work providing post-hoc explanations for model predictions, there has been relatively little work exploring more directly interpretable models that can match state-of-the-art accuracy. Historically, decision trees have been the gold standard in balancing interpretability and accuracy. However, recent attempts to combine decision trees with deep learning have resulted in models that (1) achieve accuracies far lower than that of modern neural networks (e.g. ResNet) even on small datasets (e.g. MNIST), and (2) require significantly different architectures, forcing practitioners pick between accuracy and interpretability.

原文作者：Alvin Wan,Lisa Dunlap,Daniel Ho,Jihan Yin,Scott Lee,Henry Jin,Suzanne Petryk,Sarah Adel Bargal,Joseph E. Gonzalez

原文鏈接：https://arxiv.org/abs/2004.00221