Ontology mapping seeks to find semantic correspondences between similar elements of different ontologies. This paper proposes a neural network based approach to search for a global optimal solution that best satisfies ontology constraints. Experiments on OAEI benchmark tests show it dramatically improves the performance of preliminary mapping results. Categories and Subject Descriptors D.2.12 [Software Engineering]: Interoperability ? Data mapping; I.2.6 [Artificial Intelligence]: Learning ? Connectionism and neural nets. General Terms Algorithms, Design, Experimentation. Keywords ontology mapping, interactive activation and competition (IAC) neural network, constraint satisfaction problem (CSP), PRIOR+