Document Type
Other
Publication Date
3-2000
Abstract
We describe N²VIS, an interactive visualization tool for feedforward neural network populations trained through evolutionary computation. N²VIS provides visualization of network attributes including topology, connection weights, weight volatility, and nodal activation levels for specific input values, as well as of genealogical relationships between different networks. Changes to network parameters can be made interactively by the user during training, and their effects are immediately visualized. These features contribute to making N²VIS an effective visualization tool for designers, users, and students of neural networks.
Suggested Citation
Streeter, Matthew J.
, Ward, Matthew O.
, Alvarez, Sergio A.
(2000). N²VIS: An Interactive Visualization Tool for Neural Networks. .
Retrieved from:
https://digitalcommons.wpi.edu/computerscience-pubs/88
DOI
WPI-CS-TR-00-11