Existing Recurrent Neural Networks (RNNs) are limited in their ability to model dynamical systems with nonlinearities and hidden internal states. Here we use our general framework...
Genetic programming evolves Lisp-like programs rather than fixed size linear strings. This representational power combined with generality makes genetic programming an interesting ...
Abstract. We study online learning algorithms that predict by combining the predictions of several subordinate prediction algorithms, sometimes called “experts.” These simple a...
Yoav Freund, Robert E. Schapire, Yoram Singer, Man...
We analyze collaborative play in an online video game, World of Warcraft, the most popular personal computer game in the United States, with significant markets in Asia and Europe...
In this paper we report on an interdisciplinary course "Computing and Art" taught at the Sabanci University, Istanbul for the first time in fall of 2004. We also present...