We present an approximate policy iteration algorithm that uses rollouts to estimate the value of each action under a given policy in a subset of states and a classifier to general...
For a network of spiking neurons that encodes information in the timing of individual spike times, we derive a supervised learning rule, SpikeProp, akin to traditional errorbackpr...
Sander M. Bohte, Joost N. Kok, Johannes A. La Pout...
ActiMates™ Barney™ represents a new form of interactive learning product for two- to five-year old children: a small computer that looks like an animated plush doll. He can be...
We consider the problem of learning the parameters of a Bayesian network from data, while taking into account prior knowledge about the signs of influences between variables. Such...
Abstract. Computer-supported collaborative knowledge creation is the continuous process of development of knowledge assets, where produced knowledge has to be assessed by the devel...