We describe a generator for hierarchical problems called the Hierarchical Problem Generator (HPG). Hierarchical problems are of interest since they constitute a class of problems ...
Edwin D. de Jong, Richard A. Watson, Dirk Thierens
This paper proposes a novel constructive learning algorithm for a competitive neural network. The proposed algorithm is developed by taking ideas from the immune system and demons...
Helder Knidel, Leandro Nunes de Castro, Fernando J...
We study contexts (terms with holes) by proposing a ‘λcalculus with holes’. It is very expressive and can encode programming constructs apparently unrelated to contexts, incl...
s for Multi-Agent Only Knowing (extended abstract) Arild Waaler1,2 and Bjørnar Solhaug3,4 1 Finnmark College, Norway 2 Dep. of Informatics, University of Oslo, Norway 3 SINTEF ICT...
A general model is proposed for studying ranking problems. We investigate learning methods based on empirical minimization of the natural estimates of the ranking risk. The empiric...