We consider incorporating action elimination procedures in reinforcement learning algorithms. We suggest a framework that is based on learning an upper and a lower estimates of th...
Future collaborative learning technologies are characterized by the CSCL community as highly malleable and flexible. A promising approach for meeting these expectations is to use ...
Abstract. Iterative learning is a model of language learning from positive data, due to Wiehagen. When compared to a learner in Gold's original model of language learning from...
Parallel data in the domain of interest is the key resource when training a statistical machine translation (SMT) system for a specific purpose. Since ad-hoc manual translation c...
Prasanth Kolachina, Nicola Cancedda, Marc Dymetman...
The CELEBRATEproject developed and successfully demonstrated a federated learning object brokerage system architecture and made available to schools over 1350 learning objects prod...