TY - GEN
T1 - Supervised learning in CINets
AU - Bruhn, Paul
AU - Weinschenk, Jeffrey
PY - 2011
Y1 - 2011
N2 - Continuous Inference Networks (CINets), a form of multilayer fuzzy value networks, allow computation with fuzzy values in concise structures, are capable of universal function approximation, and are readily interpretable through natural language, aiding maintenance, modification, collaboration, and knowledge sharing. However CINets have been reliant on Subject Matter Expertise (SME) and manual tuning to realize optimal performance, limiting their applicability. With ONR support[i], ARL has developed a supervised learning process for CINets, capable of designing a CINet structure, and of optimizing an existing CINet structure. The CINet supervised learning process allows the automated development of data fusion, classification, and pattern recognition structures that are interpretable, modifiable, and concise. Performance of CINets developed with the supervised learning process is compared to that of Artificial Neural Network (ANNs), fuzzy logic rule set, and Bayesian network approaches.
AB - Continuous Inference Networks (CINets), a form of multilayer fuzzy value networks, allow computation with fuzzy values in concise structures, are capable of universal function approximation, and are readily interpretable through natural language, aiding maintenance, modification, collaboration, and knowledge sharing. However CINets have been reliant on Subject Matter Expertise (SME) and manual tuning to realize optimal performance, limiting their applicability. With ONR support[i], ARL has developed a supervised learning process for CINets, capable of designing a CINet structure, and of optimizing an existing CINet structure. The CINet supervised learning process allows the automated development of data fusion, classification, and pattern recognition structures that are interpretable, modifiable, and concise. Performance of CINets developed with the supervised learning process is compared to that of Artificial Neural Network (ANNs), fuzzy logic rule set, and Bayesian network approaches.
UR - http://www.scopus.com/inward/record.url?scp=80052517855&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=80052517855&partnerID=8YFLogxK
M3 - Conference contribution
AN - SCOPUS:80052517855
SN - 9781457702679
T3 - Fusion 2011 - 14th International Conference on Information Fusion
BT - Fusion 2011 - 14th International Conference on Information Fusion
T2 - 14th International Conference on Information Fusion, Fusion 2011
Y2 - 5 July 2011 through 8 July 2011
ER -