CMU Artificial Intelligence Repository
Home INFO Search FAQs Repository Root

HYPERPLANE ANIMATOR: Graphical display of backpropagation training data and weights

The HYPERPLANE ANIMATOR is a program that allows convenient graphical display of the training data and weights in a back-propagation neural network. As learning progresses and the weights in a neural net alter, the hyperplane positions move. At the end of the training they are in positions that roughly divide training data into partitions, each of which contains only one class of data. Observations of hyperplane movement can yield valuable insights into neural network learning. The system currently animates only hyperplanes representing input-to-hidden weights.
      [] as the file hyperplane-animator.tar. (openwindows version)

Version: 1.01 (10-OCT-93) Requires: Motif toolkit on an IBM RS6000 with X-Windows. C. Copying: Use, copying, and distribution permitted provided the program is not sold for profit. CD-ROM: Prime Time Freeware for AI, Issue 1-1 Author(s): Lori Y. Pratt Steve Nicodemus Department of Mathematical and Computer Sciences Colorado School of Mines 402 Stratton Golden, CO 80401 Tel: (303) 273-3878 Keywords: Authors!Nicodemus, Authors!Pratt, Backpropagation, C!Code, Hyperplane Animator, Machine Learning!Neural Networks, Neural Networks!Visualization, Visualization References: ?
Last Web update on Mon Feb 13 10:25:03 1995