NBDT: Neural-Backed Decision Tree

NBDT: Neural-Backed Decision Tree

Machine learning applications such as finance and medicine demand accurate and justifiable predictions, barring most deep learning methods from use. In response, previous work combines decision trees with deep learning, yielding models that (1) sacrifice interpretability for accuracy or (2) sacrifice accuracy for interpretability.We forgo this dilemma by jointly improving accuracy and interpretability using Neural-Backed Decision Trees (NBDTs). NBDTs replace a neural network's final linear layer with a differentiable sequence of decisions and a surrogate loss. This forces the model to learn high-level concepts and lessens reliance on highly-uncertain decisions, yielding (1) accuracy: NBDTs match or outperform modern neural networks on CIFAR, ImageNet and better generalize to unseen classes by up to 16%. Furthermore, our surrogate loss improves the original model's accuracy by up to 2%. NBDTs also afford (2) interpretability: visual evidence of generalization, uncovering ambiguous ImageNet labels, and improving human trust.

NBDT：神经支持决策树

诸如金融和医学之类的机器学习应用程序需要准确且合理的预测，从而禁止使用大多数深度学习方法。作为响应，先前的工作将决策树与深度学习相结合，产生了以下模型：（1）为了准确性而牺牲了可解释性，或者（2）为了准确性而牺牲了准确性。.. 我们通过使用神经支持决策树（NBDT）共同提高准确性和可解释性来避免这一难题。NBDT用可区分的决策序列和替代损耗代替了神经网络的最终线性层。这迫使模型学习高级概念并减少对高度不确定的决策的依赖，从而产生（1）准确性：NBDT在CIFAR，ImageNet上与现代神经网络相匹配或胜过现代神经网络，并且可以更好地推广到看不见的类别，最高可达16％。此外，我们的替代损耗将原始模型的准确性提高了2％。NBDT还提供（2）可解释性：泛化的可视化证据，发现模糊的ImageNet标签以及提高人们的信任度。 （阅读更多）