Ryohei Nakano's Refereed International Conference Papers

[C01] R. Nakano:
Integrity checking in a logic-oriented ER model,
Proc. of the 3rd International Conference on ER Approach (ER '83),
pp.551-564 (1983).

[C02] R. Nakano and M. Kiyama:
MACH: Much faster associative machine,
Proc. of the 5th International Workshop on Database Machines (IWDM '87),
pp.339-352 (1987).

[C03] K. Saito and R. Nakano:
Medical diagnostic expert system based on PDP model,
Proc. of International Conference on Neural Networks (ICNN '88),
Vo.1, pp.255-262 (1988).

[C04] K. Saito and R. Nakano:
Rule extraction from facts and neural nets,
Proc. of International Neural Networks Conference (INNC '90),
pp.379-382 (1990).

[C05] R. Nakano and T. Yamada:
Conventional genetic algorithm for job shop problems,
Proc. of International Conference on Genetic Algorithms (ICGA '91),
pp.474-479 (1991).

[C06] R. Nakano, K. Saito, M. Ohta and S.I. Gallant:
DREAM: A heuristic approach to hypersphere minimum covering,
Proc. of International Conference on Artificial Neural Networks (ICANN '91),
pp.427-432 (1991).

[C07] T. Yamada and R. Nakano:
A genetic algorithms applicable to large-scale job-shop problems,
Proc. of the 2nd Parallel Problem Solving from Nature (PPSN '92),
pp.281-290 (1992).

[C08] N. Ueda and R. Nakano:
A competitive & selective learning method for designing optimal vector quantizers,
Proc. of International Conference on Neural Networks (ICNN '93),
pp.1444-1450 (1993).

[C09] Y. Davidor, T. Yamada and R. Nakano:
The ecological framework II: improving GA performance with virtually zero cost,
Proc. of International Conference on Genetic Algorithms (ICGA '93),
pp.171-176 (1993).

[C10] N. Ueda and R. Nakano:
A new learning approach based on equidistortion principle for optimal vector quantizer design,
Proc. of International Workshop on Neural Networks for Signal Processing (NNSP '93),
pp.362-371 (1993).

[C11] K. Saito and R. Nakano:
A concept learning algorithm with adaptive search,
Proc. of Machine Intelligence (MI) 14 Workshop (1993),
Machine Intelligence 14, pp.347-363 (1995).

[C12] T. Yamada, B.E. Rosen and R. Nakano:
A simulated annealing approach to job sop sheduling using critical block transition operation,
Proc. of International Conference on Neural Networks (ICNN '94),
pp.4687-4692 (1994).

[C13] K. Saito and R. Nakano:
Adaptive concept learning algorithm,
Proc. of the 13th World Computer Congress (IFIP '94),
pp.294-299 (1994).

[C14] R. Nakano, Y. Davidor and T. Yamada:
Optimal population size under constant computation cost,
Proc. of the 3rd Parallel Problem Solving from Nature (PPSN '94),
pp.130-138 (1994).

[C15] N. Ueda and R. Nakano:
Mixture density estimation via EM algorithm with deterministic annealing,
Proc. of International Workshop on Neural Networks for Signal Processing (NNSP '94),
pp.69-77 (1994).

[C16] N. Ueda and R. Nakano:
Deterministic annealing variant of the EM algorithm,
Proc. of Neural Information Processing Systems Conference (NIPS '94),
pp.545-552 (1994).

[C17] T. Yamada and R. Nakano:
Job-shop scheduling by simulated annealing combined with deterministic local search,
Proc. of the 1st Metaheuristics International Conference (MIC '95),
pp.344-349 (1995),
also in Meta-Heuristics: Theory & Applications, Kluwer Academic Publishers,
pp.237-248 (1996).

[C18] T. Yamada and R. Nakano:
A genetic algorithm with multi-step crossover for job-shop scheduling problems,
Proc. of International Conference on Genetic Algorithms in Engneering Systems (GALESIA '95),
pp.146-151 (1995).

[C19] K. Saito and R. Nakano:
A connectionist approach to numeric law discovery,
Proc. of Machine Intelligence (MI) 15 Workshop (1995),
Machine Intelligence 15, pp.315-327 (2000).

[C20] N. Ueda and R. Nakano:
A new maximum likelihood training and application to deterministic neural networks,
Proc. of International Conference on Artificial Neural Networks (ICANN '95),
pp.497-502 (1995).

[C21] R. Nakano, N. Ueda, K. Saito and T. Yamada:
Parrot-like speaking using optimal vector quantization,
Proc. of International Conference on Neural Networks (ICNN '95),
pp.2871-2875 (1995).

[C22] N. Ueda and R. Nakano:
Estimating expected error rates of neural networks classifiers in small sample size situations:
A Comparison of Cross-Validation and Bootstrap,
Proc. of International Conference on Neural Networks (ICNN '95),
pp.101-104 (1995).

[C23] M. Kimura and R. Nakano:
Learning dynamical systems from trajectories by continuous time recurrent neural networks,
Proc. of International Conference on Neural Networks (ICNN '95),
pp.2992-2997 (1995).

[C24] P. Esteves and R. Nakano:
Hierarchical mixture of experts and max-min propagation neural networks,
Proc. of International Conference on Neural Networks (ICNN '95),
pp.651-656 (1995).

[C25] R. Nakano, N. Ueda, K. Saito and M. Takahashi:
Wall map building from fragmentary sonar data,
Proc. of RoboLearn '96 Workshop,
pp.84-89 (1996).

[C26] N. Ueda and R. Nakano:
Generalized error of ensemble estimators,
Proc. of International Conference on Neural Networks (ICNN '96),
pp.90-95 (1996).

[C27] K. Saito and R. Nakano:
A constructive learning algorithm for an HME,
Proc. of International Conference on Neural Networks (ICNN '96),
pp.1268-1273 (1996).

[C28] T. Yamada and R. Nakano:
Scheduling by genetic local search with multi-step crossover,
Proc. of the 4th Parallel Problem Solving from Nature (PPSN '96),
pp.960-969 (1996).

[C29] M. Kimura and R. Nakano:
Learning dynamical systems produced by recurrent neural networks,
Proc. of International Conference on Artificial Neural Networks (ICANN '96),
pp.133-138 (1996).

[C30] K. Arai and R. Nakano:
Annealed RNN learning of finite state automata,
Proc. of International Conference on Artificial Neural Networks (ICANN '96),
pp.519-524 (1996).

[C31] K. Saito and R. Nakano:
Second-order learning algorithm with squared penalty term,
Proc. of Neural Information Processing Systems Conference (NIPS '96),
pp.627-633 (1996).

[C32] K. Saito and R. Nakano:
Law discovery using neural networks,
Proc. of NIPS '96 Rule-Extraction Workshop,
pp.62-69 (1996).

[C33] K. Saito and R. Nakano:
MDL regularizer: a new regularizer based on MDL principle,
Proc. of International Conference on Neural Networks (ICNN '97),
pp.1833-1838 (1997).

[C34] K. Saito and R. Nakano:
Law discovery using neural networks,
Proc. of the 15th International Joint Conference on Artificial Intelligence (IJCAI '97),
pp.1078-1083 (1997).

[C35] N. Ueda and R. Nakano:
Combining discriminant-based classifiers using the minimum classification error discriminant,
Proc. of International Workshop on Neural Networks for Signal Processing (NNSP '97),
pp.365-374 (1997).

[C36] M. Kimura and R. Nakano:
Unique representations of dynamical systems produced by recurrent neural networks,
Proc. of International Conference on Artificial Neural Networks (ICANN '97),
pp.403-408 (1997).

[C37] K. Arai and R. Nakano:
Adaptive beta scheduling learning method of finite state automata by recurrent neural networks,
Proc. of the 4th International Conference on Neural Information Processing (ICONIP '97),
pp.351-354 (1997).

[C38] K. Saito and R. Nakano:
Numeric law discovery using neural networks,
Proc. of the 4th International Conference on Neural Information Processing (ICONIP '97),
pp.843-846 (1997).

[C39] K. Yoshimura and R. Nakano:
Genetic algorithm for information operator scheduling,
Proc. of International Conference on Evolutionary Computation (ICEC '98),
pp.277-282 (1998).

[C40] N. Ueda, R. Nakano, Z. Ghahramani and G.E. Hinton:
Split and merge EM algorithm for improving Gaussian mixture density estimates,
Proc. of International Workshop on Neural Networks for Signal Processing (NNSP '98),
pp.274-283 (1998).

[C41] R. Nakano and K. Saito:
Computational characteristics of law discovery using neural networks,
Proc. of the 1st International Conference on Discovery Science (DS '98),
Lecture Notes in AI 1532, pp.342-351 (1998).

[C42] M. Kimura and R. Nakano:
Simplifying fully recurrent neural networks that have learned dynamical systems,
Proc. of International Conference on Computational Intelligence and Neuro Science (ICCIN '98),
pp.143-146 (1998).

[C43] K. Arai and R. Nakano:
Bayesian learning of finite state machine with consideration of internal state representation,
Proc. of International Conference on Computational Intelligence and Neuro Science (ICCIN '98),
pp.139-142 (1998).

[C44] N. Ueda and R. Nakano and Z. Ghahramani and G.E. Hinton:
SMEM algorithm for mixture models,
Proc. of Neural Information Processing Systems Conference (NIPS '98),
pp.599-605 (1998).

[C45] T. Yamada and K. Yoshimura and R. Nakano:
Information operator scheduing by genetic algorithms,
Proc. of the 2nd Asia-Pacific Conference on Simulated Evolution and Learning (SEAL '98),
pp.50-57 (1998).

[C46] N. Ueda and R. Nakano and Z. Ghahramani and G.E. Hinton:
Pattern classification using a mixture of factor analyzers,
Proc. of International Workshop on Neural Networks for Signal Processing (NNSP '99),
pp.525-534 (1999).

[C47] R. Nakano and K. Saito:
Discovery of a set of nominally conditioned polynomials,
Proc. of the 2nd International Conference on Discovery Science (DS '99),
Lecture Notes in AI 1721, pp.287-298 (1999).

[C48] K. Saito and R. Nakano:
Discovery of relevant weights by minimizing cross-validation error,
Proc. of the 4th Pacific-Asia Conference on Knowledge Discovery and Data Mining (PAKDD 2000),
Lecture Notes in AI 1805, pp.372-375 (2000).

[C49] K. Yoshimura, H. Kubotani and R. Nakano:
Probabilistic search for multi-objective optimization problems,
Proc. of Information & Knowledge Management in the 21st Century (INFORMS & KORMS 2000),
pp.2168-2174 (2000).

[C50] R. Nakano:
Efficient learning of behavioral rules,
Proc. of SAB2000 Proceedings Supplement, Paris,
pp.178-184 (2000).

[C51] K. Saito and R. Nakano:
Discovery of nominally conditioned polynomials using neural networks, vector quantization, and decision trees,
Proc. of the 3rd International Conference on Discovery Science (DS '00),
Lecture Notes in AI 1967, pp.325-329 (2000).

[C52] R. Nakano and K. Saito:
Finding polynomials to fit multivariate data having numeric and nominal variables,
Proc. of the 4th International Conference on Intelligent Data Analysis (IDA '01), Cascais, Portugal,
Lecture Notes in CS 2189, pp.258-267 (2001).

[C53] M. Takada and R. Nakano:
Multi-thread search with deterministic annealing EM algorithm,
Proc. of the 2002 International Joint Conference on Neural Networks (IJCNN '02), Honolulu,
pp.1034-1038 (2002).

[C54] T. Nagata and A. Kawata and K. Yamada and R. Nakano:
Neural network pruning using MV regularizer,
Proc. of the 2002 International Joint Conference on Neural Networks (IJCNN '02), Honolulu,
pp.1039-1044 (2002).

[C55] T. Yokoyama and K. Takeshima and R. Nakano:
Model selection and local optimality in learning dynamical sysmtes using recurrent neural networks,
Proc. of the 2002 International Joint Conference on Neural Networks (IJCNN '02), Honolulu,
pp.1051-1055 (2002).

[C56] K. Saito and R. Nakano:
Structuring neural networks through bidirectional clustering of weights,
Proc. of the 5th International Conference on Discovery Science (DS '02),
Lecture Notes in CS 2534, pp.206-219 (2002).

[C57] M. Takada and R. Nakano:
Threshold-based dynamic annealing for multi-thread DAEM and its extreme,
Proc. of the 2003 International Joint Conference on Neural Networks (IJCNN '03), Portland,
pp.501-506 (2003).

[C58] K. Ito and R. Nakano:
Optimizing support vector regression hyperparameters based on cross-validation,
Proc. of the 2003 International Joint Conference on Neural Networks (IJCNN '03), Portland,
pp.2077-2082 (2003).

[C59] T. Kawai and R. Nakano:
Threshold-based multi-thread EM algorithm,
Proc. of the 2004 International Joint Conference on Neural Networks (IJCNN '04), Budapest,
pp.1051-1056 (2004).

[C60] K. Saito and R. Nakano:
Extracting characteristic words of text using neural networks,
Proc. of the 2004 International Joint Conference on Neural Networks (IJCNN '04), Budapest,
pp.1397-1402 (2004).

[C61] Y. Tanahashi and K. Saito and R. Nakano:
Piecewise multivariate polynomials using a four-layer perceptron,
Proc. of the 8th International Conference on Knowledge-based Intelligent Information &
Engineering Systems (KES '04), Wellington, New Zealand,
pp.602-608 (2004).

[C62] S. Tanimoto and R. Nakano:
Learning an evaluation function for shogi from data of games,
Proc. of the 8th International Conference on Knowledge-based Intelligent Information &
Engineering Systems (KES '04), Wellington, New Zealand,
pp.609-615 (2004).

[C63] K. Kobayashi and R. Nakano:
Faster optimization of SVM hyperparameters based on minimizing cross-validation error,
Proc. of the 2004 IEEE Conference on Cybernetics and Intelligent Systems (CIS '04),
pp.1021-1026 (2004).

[C64] Y. Tanahashi, X. Chin, K. Saito and R. Nakano:
Finding a succinct multi-layer perceptron having shared weights,
Proc. of the 2005 International Joint Conference on Neural Networks (IJCNN '05), Montreal,
pp.1418-1423 (2005).

[C65] K. Kobayashi, D. Kitakoshi and R. Nakano:
Yet faster method to optimize SVR hyperparameters based on minimizing cross-validation error,
Proc. of the 2005 International Joint Conference on Neural Networks (IJCNN '05), Montreal,
pp.871-876 (2005).

[C66] K. Saito and R. Nakano:
Weight sharing on naive Bayes document model,
Proc. of the 2005 International Joint Conference on Neural Networks (IJCNN '05), Montreal,
pp.576-581 (2005).

[C67] Y. Tanahashi, K. Saito and R. Nakano:
Model selection and weight sharing of multi-layer perceptron,
Proc. of the 9th International Conference on Knowledge-based Intelligent Information &
Engineering Systems (KES '05), Melbourne,
pp.716-722 (2005).

[C68] Y. Ishikawa and R. Nakano:
Landscape of a likelihood surface for a {G}aussian mixture and its use for the EM algorithm,
Proc. of the 2006 International Joint Conference on Neural Networks (IJCNN '06), Vancouver,
pp.2413-2419 (2006).

[C69] M. Karasuyama, D. Kitakoshi and R. Nakano:
Revised optimizer of a SVM hyperparameters minimizing cross-validation error,
Proc. of the 2006 International Joint Conference on Neural Networks (IJCNN '06), Vancouver,
pp.711-718 (2006).

[C70] Y. Tanahashi, K. Saito, D. Kitakoshi and R. Nakano:
Finding nominally conditioned multivariate polynomials using a four-layer perceptron having shared weights,
Proc. of the 10th International Conference on Knowledge-based Intelligent Information &
Engineering Systems (KES '06), Bournemouth, UK,
Lecture Notes in AI 4252, pp. 969-976 (2006).

[C71] K. Saito and R. Nakano:
Improving convergence performance of pagerank computation based on step-length calculation approach,
Proc. of the 10th International Conference on Knowledge-based Intelligent Information &
Engineering Systems (KES '06), Bournemouth, UK,
Lecture Notes in AI 4252, pp. 945-952 (2006).

[C72] Y. Yan, Y. Tanahashi and R. Nakano:
A set of linear regressions with automatic nominal space partition using a four-layer perceptron,
Proc. of International Conference on Artificial Intelligence and Applications (ICAIA'07) in the IMECS2007,
pp. 53-58 (2007).

[C73] M. Kimura, K. Saito and R. Nakano:
Extracting influential nodes for information diffusion on a social network,
Proc. of the 22nd National Conference on Artificial Intelligence (AAAI'07),
pp.1371-1376 (2007).

[C74] Y. Ishikawa and R. Nakano:
Obtaining EM initial points by using the primitive initial points and subsampling strategy,
Proc. of the 2007 International Joint Conference on Neural Networks (IJCNN '07),
pp.1305(1)-1305(6) (2007).

[C75] M. Karasuyama and R. Nakano:
Optimizing SVR hyperparameters via fast cross-validation using AOSVR,
Proc. of the 2007 International Joint Conference on Neural Networks (IJCNN '07),
pp.1322(1)-1322(6) (2007).

[C76] K. Saito, R. Nakano and M. Kimura:
Prediction of link attachments by estimating probabilities of information propagation,
Proc. of the 11th International Conference on Knowledge-based Intelligent Information &
Engineering Systems (KES '07), Vietri Sul Mare, Italy,
Lecture Notes in AI 4694, pp. 235-242 (2007).

[C77] Y. Tanahashi, D. Kitakoshi and R. Nakano:
Nominally piecewise multiple regression using a four-layer perceptron,
Proc. of the 11th International Conference on Knowledge-based Intelligent Information &
Engineering Systems (KES '07), Vietri Sul Mare, Italy,
Lecture Notes in AI 4694, pp. 218-226 (2007).

[C78] K. Inagaki and R. Nakano:
Learning evaluation functions of shogi positions from different sets of games,
Proc. of the 11th International Conference on Knowledge-based Intelligent Information &
Engineering Systems (KES '07), Vietri Sul Mare, Italy,
Lecture Notes in AI 4694, pp. 210-217 (2007).

[C79] M. Karasuyama and R. Nakano:
Optimizing sparse kernel ridge regression hyperparameters based on leave-one-out cross-validation,
Proc. of the 2008 International Joint Conference on Neural Networks (IJCNN '08), Hong Kong,
pp. 3463-3468 (2008).

[C80] Y. Ishikawa and R. Nakano:
EM algorithm with PIP initialization and temperature-based selection,
Proc. of the 12th International Conference on Knowledge-based Intelligent Information
& Engineering Systems (KES '08), Zagreb, Croatia,
Lecture Notes in AI 5179, pp. 58-66 (2008).

[C81] K. Satio, R. Nakano and M. Kimura:
Prediction of information diffusion probabilities for independent cascade model,
Proc. of the 12th International Conference on Knowledge-based Intelligent Information
& Engineering Systems (KES '08), Zagreb, Croatia,
Lecture Notes in AI 5179, pp. 67-75 (2008).

[C82] M. Karasuyama, I. Takeuchi and R. Nakano:
Reducing SVR support vectors by using backward deletion,
Proc. of the 12th International Conference on Knowledge-based Intelligent Information
& Engineering Systems (KES '08), Zagreb, Croatia,
Lecture Notes in AI 5179, pp. 76-83 (2008).

[C83] M. Kimura, K. Saito, R. Nakano, H. Motoda:
Finding influential nodes in a social network from information diffusion data,
Proc. of the 2nd International Workshop on Social Computing, Behavioral Modeling, and Prediction (SBP '09),
In H. Liu, J.J. Salerno, M.J. Young (eds.) Social Computing and Behavioral Modeling, pp.138-145, Springer (2009).

[C84] Y. Tanahashi and R. Nakano:
Bidirectional clustering of MLP weights for finding nominally conditioned polynomials,
Proc. of the 19th International Conference on Artificial Neural Networks (ICANN '09), Limassol, Cyprus,
Lecture Notes in CS 5769, pp. 155-164 (2009).

[C85] Y. Ishikawa, I. Takeuchi and R. Nakano:
Variational Bayes from the primitive initial point for Gaussian mixture estimation,
Proc. of the 16th International Conference on Neural Information Processing (ICONIP '09), Bangkok,
Lecture Notes in CS 5863, pp. 159-166 (2009).

[C86] N. Harada, Y. Ishikawa, I. Takeuchi and R. Nakano:
A Bayesian graph clustering approach using the prior based on degree distribution,
Proc. of the 16th International Conference on Neural Information Processing (ICONIP '09), Bangkok,
Lecture Notes in CS 5863, pp. 167-174 (2009).

[C87] Y. Tanahashi, R. Nakano, and K. Saito:
Nominally conditioned linear regression,
Proc. of the 20th International Conference on Artificial Neural Networks (ICANN '10), Thessaloniki,
Lecture Notes in CS 6354, pp. 290-293 (2010).

[C88] R. Nakano and N. Yamada:
Number theory-based induction of deterministic context-free L system grammar,
Proc. of the 2nd International Conference on Knowledge Discovery and Information Retrieval (KDIR '10), Valencia,
pp. 194-199 (2010).

[C89] R. Nakano, S. Satoh and T. Ohwaki:
Learning method utilizing singular region of multilayer perceptron,
Proc. of the 3rd International Conference on Neural Computation Theory and Applications (NCTA '11), Paris,
pp. 106-111 (2011).

[C90] S. Satoh and R. Nakano:
Eigen vector descent and line search for multilayer perceptron,
Proc. of the 2012 IAENG International Conference on Artificial Intelligence and Applications, (ICAIA '12), Hong Kong,
pp. 1-6 (2012). awarded Best Student Paper Award.

[C91] S. Suzumura and R. Nakano:
Complex-valued multilayer perceptron search utilizing eigen vector descent and reducibility mapping,
Proc. of the 22th International Conference on Artificial Neural Networks (ICANN '12), Lausanne,
Lecture Notes in CS 7553, pp. 1-8 (2012).

[C92] R. Nakano and S. Suzumura:
Grammatical induction with error correction for deterministic context-free L-systems,
Proc. of the International Conference on Machine Learning and Data Analysis (ICMLDA '12), Berkeley,
pp. 534-538 (2012). awarded Best Paper Award.

[C93] R. Nakano:
Emergent induction of deterministic context-free L-system grammar,
Proc. of the 4th International Conference on Innovations in Bio-Inspired Computing and Applications (IBICA '13), Ostrava, Czech Republic,
Advances in Intelligent Systems and Computing 237, pp. 75-84 (2013).

[C94] S. Satoh and R. Nakano:
Mutlilayer perceptron learning utilizing singular regions and search pruning,
Proc. of the International Conference on Machine Learning and Data Analysis (ICMLDA '13), Berkeley,
pp. 790-795 (2013).

[C95] S. Satoh and R. Nakano:
Complex-valued multilayer perceptron search utilizing singular regions of complex-valued parameter space,
Proc. of the 24th International Conference on Artificial Neural Networks (ICANN '14), Hamburg,
Lecture Notes in CS 8681, pp.313-320 (2014).

[C96] S. Satoh and R. Nakano:
Singularity stairs following with limited numbers of hidden units,
Proc. of the 6th International Conference on Neural Computation Theory and Applications (NCTA '14), Rome,
pp. 180-186 (2014).

[C97] R. Nakano:
Emergent induction of L-system grammar from a string with deletion-type transmutation,
Proc. of the 6th International Conference on Knowledge Discovery and Information Retrieval (KDIR '14), Rome,
pp. 397-401 (2014).

[C98] S. Satoh and R. Nakano:
Complex-valued multilayer perceptron learning using singular regions and search pruning,
Proc. of the 2015 International Joint Conference on Neural Networks (IJCNN '15), Killarney, Ireland,
pp. 1195-1200 (2015).

[C99] S. Satoh and R. Nakano:
A yet faster version of complex-valued multilayer perceptron learning using singular regions and search pruning,
Proc. of the 7th International Conference on Neural Computation Theory and Applications (NCTA '15), Lisbon, Portugal,
pp. 122-129 (2015). final version is here.

[C100] S. Satoh and R. Nakano:
How complex-valued multilayer perceptron can predict the behavior of deterministic chaos,
Proc. of the 2016 International Joint Conference on Neural Networks (IJCNN '16), Vancouver, Canada,
pp. 4118-4124 (2016).

[C101] S. Satoh and R. Nakano:
How new information criteria WAIC and WBIC worked for MLP model selection,
Proc. of the 6th International Conference on Pattern Recognition Applications and Methods (ICPRAM '17), Porto, Portugal,
pp. 105-111 (2017). (awarded the Best Paper of the Conference) final version is here.

[C102] S. Satoh and R. Nakano:
Performance of complex-valued multilayer perceptrons largely depends on learning methods,
Proc. of the 9th International Joint Conference on Computational Intelligence (IJCCI '17), Madeira, Portugal,
pp. 45-53 (2017). final version is here.

[C103] R. Nakano and S. Satoh:
Weak dependence on initialization in mixture of linear regressions,
Proc. of the International Conference on Artificial Intelligence and Applications (ICAIA '18), Hong Kong,
pp. 1-6 (2018). final version is here.

[C104] S. Satoh and R. Nakano:
A new method for learning RBF networks by utilizing singular regions,
Proc. of the 17th International Conference on Artificial Intelligence and Soft Computing (ICAISC '18), Part I, Zakopane, Poland,
Lecture Notes in AI 10841, pp. 214-225 (2018). final version is here.

[C105] S. Satoh and R. Nakano:
Faster RBF network learning utilizing singular regions,
Proc. of the 8th International Conference on Pattern Recognition Applications and Methods (ICPRAM '19), Prague, Czech Republic,
pp. 501-508 (2019). final version is here.

[C106] R. Nakano and S. Satoh:
Mixture of multilayer perceptron regressions,
Proc. of the 8th International Conference on Pattern Recognition Applications and Methods (ICPRAM '19), Prague, Czech Republic,
pp. 509-516 (2019). final version is here.

Back to Ryohei Nakano's Top Page

Last modified on: Aug 6, 2019