Visualization for Classification in Deep Neural Networks

Conference · Sun Oct 01 04:00:00 EDT 2017

OSTI ID:1407764

Chae, Junghoon ^[1]; Gao, Shang ^[1]; Ramanathan, Arvind ^[1]; Steed, Chad ^[1]; Tourassi, Georgia ^[1]

---

1. ORNL

Recently, the techniques based on Deep Neural Networks (DNNs) have achieved a great performance in classification tasks in a wide range of applications, such as image recognition and natural language processing. However, DNN developers face a lot of trial and error during the development process and spend their efforts in debugging their network model through analyzing and understanding the classification results. As such, tools are needed that help the developers not only understand the results, but also suggest the ways to improve their model. In this paper, we propose a visual analytics tool for visualizing the classification results during the iterative development pipeline of a DNN model. Our tool enables exploring the classification results from any type of neural network models, identifying misclassified samples, examining the predicted score distributions of samples, and showing how the outcomes progressively change during the training process.

• Research Organization: Oak Ridge National Laboratory (ORNL), Oak Ridge, TN (United States)
• Sponsoring Organization: USDOE; USDOE Office of Science (SC), Advanced Scientific Computing Research (ASCR) (SC-21)
• DOE Contract Number: AC05-00OR22725
• OSTI ID: 1407764
• Country of Publication: United States
• Language: English