Interpretability methods for neural networks are difficult to evaluate
because we do not understand the black-box models typically used to test them.
This paper proposes a framework in which interpretability methods are evaluated
using manually constructed networks, which we call white-box networks, whose
behavior is understood a priori. We evaluate five methods for producing
attribution heatmaps by applying them to white-box LSTM classifiers for tasks
based on formal languages. Although our white-box classifiers solve their tasks
perfectly and transparently, we find that all five attribution methods fail to
produce the expected model explanations.

提出以白盒网络作为评估标准，评估基于语言任务的 LSTM 分类器的五种赋值热图产生方法，并发现所有五种方法都无法产生预期的模型解释。

使用白盒 LSTMs 评估归因方法

Evaluating Attribution Methods using White-Box LSTMs

This report describes our submission to the ActivityNet Challenge at CVPR
2019. We use a 3D convolutional neural network (CNN) based front-end and an
ensemble of temporal convolution and LSTM classifiers to predict whether a
visible person is speaking or not. Our results show significant improvements
over the baseline on the AVA-ActiveSpeaker dataset.

本研究使用 3D 卷积神经网络和一组时间卷积和 LSTM 分类器，对可见人是否在说话进行预测，从而在 AVS-ActiveSpeaker 数据集上获得了显著的改进。