We develop improved risk bounds for function estimation with models such as single hidden layer neural nets, using a penalized least squares criterion to select the size of the mod...
Abstract. In this paper we describe a system where behavior of characters and groups of characters are determined by assigning attributes to groups and individuals hierarchically a...
The relation between autonomous and communication phases determines the throughput of parallel structured information processing systems. Such a relation depends on the algorithm w...
In modelling the development of the oculomotor control system using neural networks, it is important to determine the appropriate cost function on which to train the models. Whilst...
This paper examines the issue of developing semantics for agent communication languages. In particular, it considers the problem of giving a verifiable semantics for such language...