Journal
JOURNAL OF VISUALIZATION
Volume 25, Issue 3, Pages 593-612Publisher
SPRINGER
DOI: 10.1007/s12650-021-00809-4
Keywords
Neural network visualization; Neural network training; Deep learning; Visual analytics; Visualization
Categories
Funding
- Natural Sciences and Engineering Research Council of Canada (NSERC)
Ask authors/readers for more resources
This paper introduces neural network training fingerprint (NNTF), a visual analytics approach to investigate the training process of any neural network performing classification. NNTF can help understand how classification decisions change along the training process, displaying information about convergence, oscillations, and training rates. Its usefulness is demonstrated through case studies and its ability to support the analysis of training parameters.
The striking results of deep neural networks (DNN) have motivated its wide acceptance to tackle large datasets and complex tasks such as natural language processing, facial recognition, and artificial image generation. However, DNN parameters are often empirically selected on a trial-and-error approach without detailed information on convergence behavior. While some visualization techniques have been proposed to aid the comprehension of general-purpose neural networks, only a few explore the training process, lacking the ability to adequately display how abstract representations are formed and represent the influence of training parameters during this process. This paper describes neural network training fingerprint (NNTF), a visual analytics approach to investigate the training process of any neural network performing classification. NNTF allows understanding how classification decisions change along the training process, displaying information about convergence, oscillations, and training rates. We show its usefulness through case studies and demonstrate how it can support the analysis of training parameters.
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