Abstract— This paper proposes an approach to learn subjectindependent P300 models for EEG-based brain-computer interfaces. The P300 models are first learned using a pool of exis...
Max and min operations have interesting properties that facilitate the exchange of information between the symbolic and real-valued domains. As such, neural networks that employ m...
—We present a structured model of context that supports an integrated approach to language acquisition and use. The model extends an existing formal notation, Embodied Constructi...
Abstract— Automatic pattern classifiers that allow for incremental learning can adapt internal class models efficiently in response to new information, without having to retrai...
We present a kernel-based algorithm for hierarchical text classification where the documents are allowed to belong to more than one category at a time. The classification model is...
Craig Saunders, John Shawe-Taylor, Juho Rousu, S&a...