Demonstration of simple Neural Network (NN) setup in a system that uses Evolutionary Computation (EC) so that a population of individuals (game agents) are directed to perform dynamic optimization of inverse hill-climbing (using relatively small steps in order to visualize progress) in order to discover the lowest point on a constantly changing terrain function. Each individual does not have knowledge of how the others are performing, which means that there is no "cheating" going on; all individuals are performing on their own.
Papers featuring Neural Networks research can be found within the NSI publications directory: www.natural-selection.com
Copyright 2000-2011 Natural Selection, Inc. (R), www.natural-selection.com
Protected under U.S. Patent No. 7,025,675
Developer: Tim Hays
Papers featuring Neural Networks research can be found within the NSI publications directory: www.natural-selection.com
Copyright 2000-2011 Natural Selection, Inc. (R), www.natural-selection.com
Protected under U.S. Patent No. 7,025,675
Developer: Tim Hays
Artificial Intelligence Demos 5:
Neural Network setup & dynamic function optimization video (above)
