论文标题
神经网络是决策树
Neural Networks are Decision Trees
论文作者
论文摘要
在此手稿中，我们表明任何具有任何激活功能的神经网络都可以表示为决策树。表示形式是等效的，而不是近似值，因此完全保持神经网络的准确性。我们认为，这项工作可以更好地理解神经网络，并为解决其黑盒性质的方式铺平了道路。我们共享某些神经网络的等效树，并表明，除了提供可解释性外，树的表示还可以实现小型网络的一些计算优势。该分析既适用于完全连接的卷积网络，也可能包括或可能不包括跳过连接和/或正常化。
In this manuscript, we show that any neural network with any activation function can be represented as a decision tree. The representation is equivalence and not an approximation, thus keeping the accuracy of the neural network exactly as is. We believe that this work provides better understanding of neural networks and paves the way to tackle their black-box nature. We share equivalent trees of some neural networks and show that besides providing interpretability, tree representation can also achieve some computational advantages for small networks. The analysis holds both for fully connected and convolutional networks, which may or may not also include skip connections and/or normalizations.
