A structured organization of information is typically required by symbolic processing. On the other hand, most connectionist models assume that data are organized according to relatively poor structures, like arrays or sequences. The framework described in this paper is an attempt to unify adaptive models like artificial neural nets and belief nets for the problem of processing structured information. In particular, relations between data variables are expressed by directed acyclic graphs, where both numerical and categorical values coexist. The general framework proposed in this paper can be regarded as an extension of both recurrent neural networks and hidden Markov models to the case of acyclic graphs. In particular we study the supervised learning problem as the problem of learning transductions from an input structured space to an output structured space, where transductions are assumed to admit a recursive hidden statespace representation. We introduce a graphical formalism for r...

Nowadays the size and complexity of models is growing more and more, forcing modelers to face some problems that they were not accustomed to. Before trying to study ways to deal with complex models, a more important and primary question to explore is, is there any means to avoid the generation of complex models? The primary purpose of this paper is to discuss several issues regarding the complexity of simulation models, summarizing the findings in this area so far, and calling attention to this area that, despite its importance, appears to remain at the bottom of simulation research agendas. 1