Artificial Neural Networks and Statistical Pattern Recognition: Old and New Connections,

The current resurgence of interest in Neural Networks has opened up several basic issues. In this chapter, we explore the connections between this area and Markov Random Fields. We are speciically concerned with early vision problems which have already beneeted from a parallel and distributed computing perspective. We explore the relationships between the two elds at two diierent levels of a computational approach. Applications highlighting speciic instances where ideas from the two approaches intertwine are discussed.