Visualization of Hidden Node Activity in Neural Networks: II. Application to RBF Networks

Scatterograms of the images of training set 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. Depending on network parameters only some parts of the unit hypercube – called here admissible spaces – may be reached. The usefulness of visualization techniques is illustrated on parity problems solved with RBF networks.

• Type: Conference
• Year: 2004
• Where: ICAISC
• Authors: Wlodzislaw Duch
• Keywords: Artificial Intelligence, Hidden Space Help, ICAISC 2004, Neural Network Mappings, Training Set Vectors