In this work, we propose a general framework called Concept-Monitor to help
demystify the black-box DNN training processes automatically using a novel
unified embedding space and concept diversity metric. Concept-Monitor enables
human-interpretable visualization and indicators of the DNN training processes
and facilitates transparency as well as deeper understanding on how DNNs
develop along the during training. Inspired by these findings, we also propose
a new training regularizer that incentivizes hidden neurons to learn diverse
concepts, which we show to improve training performance. Finally, we apply
Concept-Monitor to conduct several case studies on different training paradigms
including adversarial training, fine-tuning and network pruning via the Lottery
Ticket Hypothesis

通过一个称为 Concept-Monitor 的框架以及一个新的统一的嵌入空间和概念多样性度量方法，我们提出了一个通用的框架，可以自动帮助我们了解黑箱 DNN 训练进程，并且对 DNN 培训过程进行可解释的可视化，还提出了一个新的训练正则化器，以激励隐藏神经元学习不同的概念，从而改善培训表现，并应用于敌对培训、微调和网络修剪等几个情景中。