Part of Advances in Neural Information Processing Systems 2 (NIPS 1989)
Jakub Wejchert, Gerald Tesauro
We have developed graphics to visualize static and dynamic infor(cid:173) mation in layered neural network learning systems. Emphasis was placed on creating new visuals that make use of spatial arrange(cid:173) ments, size information, animation and color. We applied these tools to the study of back-propagation learning of simple Boolean predicates, and have obtained new insights into the dynamics of the learning process.