论文标题
挑战方式的分配解释性
In-Distribution Interpretability for Challenging Modalities
论文作者
论文摘要
广泛认识到，相对于更简单的方法，深层神经网络的预测很难解析。但是，在过去的几年中，研究这种模型运营方式的方法的发展迅速发展。最近的工作引入了一个直观的框架，该框架利用生成模型来改善此类解释的有意义。在这项工作中，我们展示了这种方法来解释多种多样和挑战的方式的灵活性：城市环境的音乐和物理模拟。
It is widely recognized that the predictions of deep neural networks are difficult to parse relative to simpler approaches. However, the development of methods to investigate the mode of operation of such models has advanced rapidly in the past few years. Recent work introduced an intuitive framework which utilizes generative models to improve on the meaningfulness of such explanations. In this work, we display the flexibility of this method to interpret diverse and challenging modalities: music and physical simulations of urban environments.
