This paper presents a novel framework called proto-reinforcement learning (PRL), based on a mathematical model of a proto-value function: these are task-independent basis function...
Abstract. Certain types of database-backed web sites heavily utilize userdefined functions in SQL queries. Unfortunately, existing web proxy caching schemes can not handle these fu...
Seeking to extend the functional capability of the elderly, we explore the use of probabilistic methods to learn and recognise human activity in order to provide monitoring suppor...
The prevailing architecture for web-based applications relies on HTML, HTTP and loosely integrated functional elements, propagating a strong distinction between client and server....
In this article, we extend a local prototype-based learning model by active learning, which gives the learner the capability to select training samples and thereby increase speed a...
Frank-Michael Schleif, Barbara Hammer, Thomas Vill...