Search Results for "learn"

...Transduction, or transductive inference, tries to predict new outputs on specific and fixed (test) cases from observed, specific (training) cases. The simplest realization for transductive inference is the method of k-nearest neighbors. Learning to learn learns its own inductive bias based on previous experience. ...AND SO ON.... Enjoy the program !

This Java-application contains all required components to simulate a game of Ms. Pac-Man and let an agent learn intelligent playing behaviour using reinforcement learning and either Q-Learning or SARSA. The framework was developed by Luuk Bom and Ruud Henken, under supervision of Marco Wiering, Department of Artificial Intelligence, University of Groningen. It formed the basis of a bachelor's thesis titled "Using reinforcement learning with relative input to train Ms.

RASCALLI stands for "Responsive Artificial Situated Cognitive Agents that Live and Learn on the Internet". The primary goal is to develop software agents that assist their users in finding relevant information on the Internet.

Project Genesis brings the game of life up-to-date. instead of dots, we have animals, instead of trivial rules about close proximity dots, we model real world activities: move,eat,kill,steal,destroy,sleep, breed and learn different patterns of behavior.

An agent that tries to learn your taste in music based on an example database, using different AI-learning-approaches.

This project is for automatically rotating images based on content. This was a masters project and contains simple implementations of machine learning algorithms.