Recursive neural networks and graphs: dealing with cycles

Abstract. Recursive neural networks are a powerful tool for processing structured data. According to the recursive learning paradigm, the in-put information consists of directed positional acyclic graphs (DPAGs). In fact, recursive networks are fed following the partial order dened by the links of the graph. Unfortunately, the hypothesis of processing DPAGs is sometimes too restrictive, being the nature of some real{world problems intrinsically cyclic. In this paper, the methodology proposed in [1, 2] to process cyclic directed graphs is tested on some interesting problems in the eld of structural pattern recognition. Such preliminary experimentation shows very promising results.