Humans are able to explain their reasoning. On the contrary, deep neural networks are not. This paper attempts to bridge this gap by introducing a new way to design interpretable neural networks for classification, inspired by physiological evidence of the human visual system's inner-workings. This paper proposes a neural network design paradigm, termed InterpNET, which can be combined with any existing classification architecture to generate natural language explanations of the classifications. The success of the module relies on the assumption that the network's computation and reasoning is represented in its internal layer activations. While in principle InterpNET could be applied to any existing classification architecture, it is evaluated via an image classification and explanation task. Experiments on a CUB bird classification and explanation dataset show qualitatively and quantitatively that the model is able to generate high-quality explanations. While the current state-of-the-art METEOR score on this dataset is 29.2, InterpNET achieves a much higher METEOR score of 37.9.

本文提出了一种新的解释性神经网络框架，可以生成自然语言的分类解释，试图弥合人类推理和深度神经网络推理相差的鸿沟。该模型在 CUB 鸟类分类和解释数据集上获得了 METEOR 分数 37.9，为目前最高水平。

InterpNET: 可解释深度学习的神经内视