资源分类
》 资源 》论文》A Benchmark for Interpretability Methods in Deep Neural Networks

A Benchmark for Interpretability Methods in Deep Neural Networks

2020-02-25 | |  71 |   36 |   0

Abstract

We propose an empirical measure of the approximate accuracy of feature importance estimates in deep neural networks. Our results across several large-scale image classification datasets show that many popular interpretability methods produce estimates of feature importance that are not better than a random designation of feature importance. Only certain ensemble based approaches—VarGrad and SmoothGrad-Squared—outperform such a random assignment of importance. The manner of ensembling remains critical, we show that some approaches do no better then the underlying method but carry a far higher computational burden.

上一篇：Online Normalization for Training Neural Networks

下一篇：Think Globally, Act Locally: A Deep Neural Network Approach to High-Dimensional Time Series Forecasting

用户评价
全部评价

热门资源

  • The Variational S...

    Unlike traditional images which do not offer in...

  • Learning to Predi...

    Much of model-based reinforcement learning invo...

  • Stratified Strate...

    In this paper we introduce Stratified Strategy ...

  • A Mathematical Mo...

    Direct democracy, where each voter casts one vo...

  • Rating-Boosted La...

    The performance of a recommendation system reli...