In this paper, we apply an evolutionary algorithm to learning behavior on a novel, interesting task to explore the general issue of learning e ective behaviors in a complex enviro...
We present a method which uses example pairs of equal or unequal class labels to select a subspace with near optimal metric properties in a kernel-induced Hilbert space. A represen...
We present a simple, agnostic active learning algorithm that works for any hypothesis class of bounded VC dimension, and any data distribution. Our algorithm extends a scheme of C...
Embodied artificial intelligence argues that the body and brain play equally important roles in the generation of adaptive behavior. An increasingly common approach therefore is to...
Abstract. We give dimension-free and data-dependent bounds for linear multi-task learning where a common linear operator is chosen to preprocess data for a vector of task speci...c...