Data processing: artificial intelligence – Neural network
Reexamination Certificate
2007-10-09
2007-10-09
Vincent, David (Department: 2129)
Data processing: artificial intelligence
Neural network
C706S019000, C702S006000
Reexamination Certificate
active
10811403
ABSTRACT:
A system and method for generating a neural network ensemble. Conventional algorithms are used to train a number of neural networks having error diversity, for example by having a different number of hidden nodes in each network. A genetic algorithm having a multi-objective fitness function is used to select one or more ensembles. The fitness function includes a negative error correlation objective to insure diversity among the ensemble members. A genetic algorithm may be used to select weighting factors for the multi-objective function. In one application, a trained model may be used to produce synthetic open hole logs in response to inputs of cased hole log data.
REFERENCES:
patent: 5251286 (1993-10-01), Wiener et al.
patent: 5444619 (1995-08-01), Hoskins et al.
patent: 5828981 (1998-10-01), Callender et al.
patent: 5862513 (1999-01-01), Mezzatesta et al.
patent: 2002/0152030 (2002-10-01), Schultz et al.
“Modeling of Sonic Logs in Oil Wells with Neural Network Ensembles”, P.M. Granitto, P.F. Verdes, H.D. Navone, H.A. Ceccatto, D. Curia and C. Larriestra, Argentine Symposium on Artificial Intelligence (ASAI'01) (Bs. As., Sep. 12-13, 2001). http://citeseer.ist.psu.edu/granitto01modeling.html.
“Modular artificial neural network for prediction of petrophysicalproperties from well log data”,C. C. Fung, K. W. Wong. H. Eren, R. Charlebois, H. Crocket, IEEE Intstrumentation & Measurement Tech Conf, 1996.
“Ensemble learning via negative correlation”, Y. Liu, X. Yao, Neural Networks, vol. 12 , Issue 10 (Dec. 1999), pp. 1399-1404.
“A Genetic Algorithm Approach for Creating Neural-Network Ensembles”, D. W. Opitz, J. W. Shavlik, Combining Articial Neural Nets, pp. 79-99. Springer-Verlag, London, 1999. http://citeseer.ist.psu.edu/opitz99genetic.html.
“Evolutionary ensembles with negative correlation learning”, Y. Liu, X. Yao, T. Higuchi, IEEE Transactions on Evolutionary Computation, Nov. 2000, vol. 4, No. 4, pp. 380-387.
“Negative Correlation Learning and the Ambiguity Family of Ensemble Methods”, G. Brown, J. Wyatt, Springer-Verlag Berlin Heidelberg 2003.
Md. Monirul Islam, et al.,A Constructive Algorithm for Training Cooperative Neural Network Ensembles, Jul. 2003, pp. 820-834, IEEE Transactions on Neural Networks, vol. 14, No. 4.
Gaspar-Cunha, A.RPSGAe—Reduced Pareto Set Genetic Algorithm: A Multiobjective Genetic Algorithm with Elitism, Nov. 2002, Six pages, Workshop on Multiple Objective Metaheuristics, Carre des Sciences, Paris, France.
R. M. Everson, et al.,Full Elite-Sets for Multi-objective Optimisation, 2002, Eight pages, Fifth International Conference on Adaptive Computing in Design and Manufacture (ACDM 2002).
Zhi-Hua Zhou, et al.,Genetic Algorithm based Selective Neural Network Ensemble, 2001, vol. 2, pp. 797-802, 17thInternational Joint Conference on Artificial Intelligence, Seattle, WA.
Chen Dingding
Hamid Syed
Smith, Jr. Harry D.
Halliburton Energy Service,s Inc.
Krueger Iselin LLP
Tran Mai T
Vincent David
LandOfFree
Genetic algorithm based selection of neural network ensemble... does not yet have a rating. At this time, there are no reviews or comments for this patent.
If you have personal experience with Genetic algorithm based selection of neural network ensemble..., we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Genetic algorithm based selection of neural network ensemble... will most certainly appreciate the feedback.
Profile ID: LFUS-PAI-O-3901306