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.
CITATION STYLE
Piȩkniewski, F., & Rybicki, L. (2004). Visualizing and analyzing multidimensional output from MLP networks via barycentric projections. In Lecture Notes in Artificial Intelligence (Subseries of Lecture Notes in Computer Science) (Vol. 3070, pp. 247–252). Springer Verlag. https://doi.org/10.1007/978-3-540-24844-6_33
Mendeley helps you to discover research relevant for your work.