We prove the strongest known bound for the risk of hypotheses selected from the ensemble generated by running a learning algorithm incrementally on the training data. Our result i...
We propose a method of knowledge reuse for an ensemble of genetic programming-based learners solving a visual learning task. First, we introduce a visual learning method that uses...
Wojciech Jaskowski, Krzysztof Krawiec, Bartosz Wie...
In this paper we construct an atlas that captures functional characteristics of a cognitive process from a population of individuals. The functional connectivity is encoded in a lo...
Georg Langs, Danial Lashkari, Andrew Sweet, Yanmei...
We study the effects of various emergent topologies of interaction on the rate of language convergence in a population of communicating agents. The agents generate, parse, and lea...
In this paper, it is shown how to extract a hypothesis with small risk from the ensemble of hypotheses generated by an arbitrary on-line learning algorithm run on an independent an...