arXiv Analytics

Sign in

arXiv:1710.05285 [cs.LG]AbstractReferencesReviewsResources

CNNComparator: Comparative Analytics of Convolutional Neural Networks

Haipeng Zeng, Hammad Haleem, Xavier Plantaz, Nan Cao, Huamin Qu

Published 2017-10-15Version 1

Convolutional neural networks (CNNs) are widely used in many image recognition tasks due to their extraordinary performance. However, training a good CNN model can still be a challenging task. In a training process, a CNN model typically learns a large number of parameters over time, which usually results in different performance. Often, it is difficult to explore the relationships between the learned parameters and the model performance due to a large number of parameters and different random initializations. In this paper, we present a visual analytics approach to compare two different snapshots of a trained CNN model taken after different numbers of epochs, so as to provide some insight into the design or the training of a better CNN model. Our system compares snapshots by exploring the differences in operation parameters and the corresponding blob data at different levels. A case study has been conducted to demonstrate the effectiveness of our system.

Comments: 5 pages. This paper has been accepted by VADL 2017: Workshop on Visual Analytics for Deep Learning
Categories: cs.LG, cs.CV
Subjects: H.1.2
Related articles: Most relevant | Search more
arXiv:1511.06067 [cs.LG] (Published 2015-11-19)
Convolutional neural networks with low-rank regularization
arXiv:1602.02660 [cs.LG] (Published 2016-02-08)
Exploiting Cyclic Symmetry in Convolutional Neural Networks
arXiv:1905.04967 [cs.LG] (Published 2019-05-13)
Implicit Filter Sparsification In Convolutional Neural Networks