Journal
IEEE TRANSACTIONS ON VISUALIZATION AND COMPUTER GRAPHICS
Volume 24, Issue 1, Pages 77-87Publisher
IEEE COMPUTER SOC
DOI: 10.1109/TVCG.2017.2744938
Keywords
deep learning; deep generative models; blue noise sampling; credit assignment
Categories
Funding
- National NSF of China [61672308, 61620106010, 61621136008]
- NVIDIA
- Tsinghua Tiangong Intelligent Technology Institute
Ask authors/readers for more resources
Among the many types of deep models, deep generative models (DGMs) provide a solution to the important problem of unsupervised and semi-supervised learning. However, training DGMs requires more skill, experience, and know-how because their training is more complex than other types of deep models such as convolutional neural networks (CNNs). We develop a visual analytics approach for better understanding and diagnosing the training process of a DGM. To help experts understand the overall training process, we first extract a large amount of time series data that represents training dynamics (e.g., activation changes over time). A blue-noise polyline sampling scheme is then introduced to select time series samples, which can both preserve outliers and reduce visual clutter. To further investigate the root cause of a failed training process; we propose a credit assignment algorithm that indicates how other neurons contribute to the output of the neuron causing the training failure. Two case studies are conducted with machine learning experts to demonstrate how our approach helps understand and diagnose the training processes of DGMs. We also show how our approach can be directly used to analyze other types of deep models such as CNNs.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available