Energy concerns push AI optimizations to the edge.

Neural networks are still very important part of artificial intelligence. RBF networks seems to be more powerfull than that based on sigmoid function. Error Correction is second order training algorithm dedicated for RBF networks. The paper proposes method for improvement this algorithm by elimination of inconsistent patterns. The approach is also experimentally confirmed.

K-medoids clustering algorithm is used to classify data, but the approach is sensitive to the initial selection of the centers and the divided cluster quality is not high. Basic Artificial Fish Swarm Algorithm is a new type of heuristic swarm intelligence algorithm, but optimization is difficult to get a very high precision due to the randomness of the artificial fish behavior. A novel clusteri...

The ant algorithm is a branch of the artificial intelligence, which is developed from natural rules and of strong adaptability and expandability. Compared to other conventional algorithms, the algorithm has an unparalleled advantage that is demonstrated on combinatorial optimization problems through its application in the multi-objective minimum spanning tree.

This is the written documentation of the implementation of an agent for Ms-Pac-Man for a Ms. Pac-Man simulation. The agent uses the UCT algorithm (upper confident bounds) which is becoming more prominent in the domain of artificial intelligence research. In this document you will find a description of the UCT algorithm, statements to the implementation and an evaluation of the performance.