The reward functions that drive reinforcement learning systems are generally derived directly from the descriptions of the problems that the systems are being used to solve. In so...
One-class classification naturally only provides one class of exemplars on which to construct the classification model. In this work, multiobjective genetic programming (GP) all...
An agent population can be evolved in a complex environment to perform various tasks and optimize its job performance using Learning Classifier System (LCS) technology. Due to the...
Recurrent neural networks are theoretically capable of learning complex temporal sequences, but training them through gradient-descent is too slow and unstable for practical use i...
Neural Logic Network or Neulonet is a hybrid of neural network expert systems. Its strength lies in its ability to learn and to represent human logic in decision making using comp...