Visualization of BP neural network using parallel coordinates

Authors:
Jing Zhao
Affiliations:
Women's Academy at Shandong, Jinan Shandong, China
Venue:
Proceedings of the 3rd International Symposium on Visual Information Communication
Year:
2010

Citing 6
Cited 0

Construction of line densities for parallel coordinate plots

Computing and graphics in statistics
Hierarchical parallel coordinates for exploration of large datasets

VIS '99 Proceedings of the conference on Visualization '99: celebrating ten years
Dynamic Graphics for Statistics

Dynamic Graphics for Statistics
Getting There: The Ten Top Problems Left

IEEE Computer Graphics and Applications
Clutter Reduction in Multi-Dimensional Data Visualization Using Dimension Reordering

INFOVIS '04 Proceedings of the IEEE Symposium on Information Visualization
Convergence of BP algorithm for product unit neural networks with exponential weights

Neurocomputing

Quantified Score

Hi-index	0.00

Visualization

Abstract

BP neural network is an important part of neural network, and is broadly used in many areas. For BP neural network it's essential to learn a lot of training samples. However, the dataset of the training samples is so large and multi-dimensional that traditional techniques can't convey them effectively in a relative small display area. To address this problem, a parallel coordinates-based BP network visualization technique is proposed. In this approach, the parallel coordinates is constructed according to the model of BP neural network. In particular, clusters, colors, size, density and other features are used to improve the parallel coordinates to create clear intelligible visualization. At last, an experiment is designed to argue that parallel coordinates-based BP network visualization is feasible and effective, and can reveal the relations and rules hidden in the training samples in the process of the training.