Scatterograms of images of training vectors in the hidden space help to evaluate the quality of neural network mappings and understand internal representations created by the hidden layers. Visualization of these representations leads to interesting conclusions about optimal architectures and training of such networks. The usefulness of visualization techniques is illustrated on parity problems solved with RBF networks.
CITATION STYLE
Duch, W. (2004). Visualization of hidden node activity in neural networks: II. application to RBF networks. In Lecture Notes in Artificial Intelligence (Subseries of Lecture Notes in Computer Science) (Vol. 3070, pp. 44–49). Springer Verlag. https://doi.org/10.1007/978-3-540-24844-6_6
Mendeley helps you to discover research relevant for your work.