This is the Neural Network in-class presentation. It is motivated by solving the problem of semantic interoperability in DB and Semantic Web, adopting Neural Network techniques, SEMINT and PRIOR+.
【Presentated materials】:
Li, W. and Clifton, C. Semint: A System Prototype for Semantic Integration in Heterogeneous Databases. In Proceedings of SIGMOD Conference. 1995, 484-484.
Li, W. and Clifton, C. Semantic Integration in Heterogeneous Databases Using Neural Networks. In Proceedings of VLDB. 1994, 1-12.
Li, W. and Clifton, C. SEMINT: A tool for identifying attribute correspondences in heterogeneous databases using neural networks. In Proceedings of Data Knowl. Eng.. 2000, 49-84.
Li, W., Clifton, C., and Liu, S. Database Integration Using Neural Networks: Implementation and Experiences. In Proceedings of Knowl. Inf. Syst.. 2000, 73-96.
Mao, M. Ontology Mapping: An Information Retrieval and Interactive Activation Network Based Approach. In Proceedings of ISWC/ASWC. 2007, 931-935.
Mao, M., Peng, Y., and Spring, M. Integrating the IAC neural network in ontology mapping. In Proceedings of WWW. 2008, 1223-1224.
Mao, M., Peng, Y., and Spring, M. Neural Network based Constraint Satisfaction in Ontology Mapping. In Proceedings of AAAI. 2008, 1207-1212.
Mao, M. Ph.D. Dissertation. “Ontology Mapping: Towards Semantic Interoperability in Distributed and Heterogeneous Environments”. Univ. of Pitts. 2008.
Duration : 0:7:47
http://xoax.net/
http://xoax.net/
DISCLAIMER: This video is boring. Basically this was an ignment for a class, wanted to get it up on YouTube in case the TA wanted to see it. In the rare case anyone cares to see this video, these X-Wings (the only free model I could find that wasn’t ugly as ) are controlled by a neural network. 4 inputs, a hidden layer of 3 nodes, and 4 output nodes. I could reduce the outputs down to 2, but it’s too late for that now (I’ll do it in the next project). 
Artificial neural network driven mobile robots learn how to drive on roads in simulation. The neural networks are evolved using Ken Stanley’s HyperNEAT algorithm. Computational Intelligence Group Czech technical University in Prague 2008