Visualizing and Analyzing Multidimensional Output from MLP Networks via Barycentric Projections

Barycentric plotting, achieved by placing gaussian kernels in distant corners of the feature space and projecting multidimensional output of neural network on a plane, provides information about the process of training and certain features of the network. Additional visual guides added to the plot show tendencies and irregularities in the training process.

• Type: Conference
• Year: 2004
• Where: ICAISC
• Authors: Filip Piekniewski, Leszek Rybicki
• Keywords: Additional Visual Guides, Artificial Intelligence, Distant Corners, Gaussian Kernels, ICAISC 2004