In our research, we have developed a transfer-based machine translation architecture for the translation from Japanese into German. One main feature of the system is the fully auto...
Learning to solve small instances of a problem should help in solving large instances. Unfortunately, most neural network architectures do not exhibit this form of scalability. Our...
We derive cost formulae for three di erent parallelisation techniques for training supervised networks. These formulae are parameterised by properties of the target computer archit...
In this paper, we present a principled approach to constructing believable game players that relies on a cognitive architecture. The resulting agent is capable of playing the game...
Standard learning procedures are better fitted to estimation than to classification problems, and focusing the training on appropriate samples provides performance advantages in cl...
Soufiane El Jelali, Abdelouahid Lyhyaoui, An&iacut...