Return

(2) S.Watanabe and K.Fukumizu, "Algorithms and Architectures," Academic Press, 1998.

(3) S. Watanabe, "Learning Machines and Algorithms," Kyoritsu-Shuppann (in Japanese), Volume 6 in Data Science Series, 2001.

(1) S.Watanabe, M.Yoneyama, "Ultrasonic Robot Eyes Using Neural Networks," IEEE Trans. on Ultrasonics, Ferroelectrics, and Frequency Control, Vol.37, No.3, pp.141-127, 1990.

(2) S.Watanabe, M.Yoneyama, "A three-dimensional object recognition method using acoustical imaging and neural networks," The Journal of the Acoustical Society of Japan, Vol.47, No.11, pp.825-833, 1991.

(3) S.Watanabe, M.Yoneyama, "An Ultrasonic 3-D visual Sensor Using Neural Networks", IEEE Trans. on Robotics and Automation," Vol.6, No.2, pp.240-249, 1992.

(4) S.Watanabe, M.Yoneyama, "A restoration method of acoustic images using a neural network," The Journal of the Acoustical Society of Japan, Vol.48, No.10, pp.711-719, 1992.

(5) S.Watanabe, M.Yoneyama,"A classification method of 3-D objects by a neuro-ultrasonic visual sensor using position and rotation invariant feature values," The Journal of the Acoustical Society of Japan, Vol.48, No.10, pp.720-726, 1992.

(6) K.Takatsu, H.Sawai, S.Watanabe, M.Yoneyama, "Genetic algorithms applied to Bayesian image restoration," IEICE Trans., Vol.J77-D-2, No.9, pp.1768-1777, 1994.

(7) S.Watanabe, K.Fukumizu, "Probabilistic design of Layered Neural networks based on their unified framework," IEEE Transactions on Neural Networks, Vol.6, No.3, pp.691-702, 1995.

(8) S.Watanabe, "A modified information criterion for automatic model and parameter selection in neural network learning," IEICE Transactions, Vol.E78-D, No.4, pp.490-499, 1995.

(9) S.Ishii, K.Fukumizu, S.Watanabe, "A Network of Chaotic Elements for Information Processing," Neural Networks, Vol.9, No.1, pp.25-40, 1996.

(10) S.Watanabe, "Solvable models of layered neural networks based on their differential structure," Advances in Computational Mathematics, Vol.5, No.1, pp.205-231, 1996.

(11) K.Fukumizu, S.Watanabe, "Optimal training data and predictive error of polynomial approximation," IEICE Trans., Vol.J79-A, No.5, pp.1100-1108, 1996.

(12) S.Watanabe, "A finite wavelet decomposition method," IEICE Trans., Vol.J79-A, No.12, pp.1948-1956, 1996.

(13) N. Ichimasa, Y.Yokota, S.Watanabe, "Route Optimization of Mobil Service Station by Genetic Algorithms with the Variable Number of Gene," IEICE Trans. Vol.J81-A, No.9, pp.1221-1229,1998.

(14) S.Watanabe, "On the generalization error by a layered statistical model with Bayesian estimation," IEICE Trans., Vol.J81-A, No.10, pp.1442-1452, 1998.

(15) M.Yoneyama, K.Yuasa, S.Watanabe, "Identification of system characteristics of the ultrasonic imaging system using genetic algorithm," The Journal of Acoustic Society of Japan, Vol.55, No.1,pp.3-11, 1999.

(16) S.Watanabe,"Algebraic Analysis for Non-identifiable Learning Machines," Neural Computation, Vol.13, No.4, pp.899-933, 2001 Article postscript, gzipped

(17) S. Watanabe, "Training and generalization errors of learning machines with algebraic singularities," IEICE Transactions, Vol.J84-A,No.1,pp.99-108, Jan. 2001.

(18) S. Watanabe, "Algebraic geometry of learning machines with singularities and their prior distributions," Journal of Japanese Society of Artificial Intelligence, Vol.16, No.2, pp.308-315, March, 2001 (Invited Paper).

(19) S. Watanabe, "Algebraic geometrical methods for hierarchical learning machines," Neural Networks, Vol.14, No.8,pp.1049-1060, 2001.

Article, Postscript, gzipped , figures

(20) S. Watanabe, "Learning efficiency of redundant neural networks in Bayesian estimation," IEEE Transactions on Neural Networks, Vol.12, No.6, 1475-1486,2001.

Errata: IEEE Transactions on Neural Networks, Vol.13, No.1,pp.254, 2002.

Article, Postscript, gzipped , figures

(21) K.Yamazaki, S.Watanabe,"A probabilistic algorithm to calculate the learning curves of hierarchical learning machines with singularities," Trans. on IEICE, Vol.J85-D-II,No.3,pp.363-372,Mar. 2002.

(22) K.Nishiue, S.Watanabe,"Effects of priors in model selection of learning machines with singularities," IEICE Trans., Vol.J86D-II,No.1,pp.119-129, 2003.

(23) K.Watanabe, S.Watanabe,"Upper bounds of Bayes generalization errors in reduced rank regression," IEICE Trans.,Vol.J86A, No.3 ,pp.278-287, 2003.

(24) S.Watanabe, S.-I.Amari,"Learning coefficients of layered models when the true distribution mismatches the singularities", Neural Computation, Vol.15,No.5,1013-1033, 2003.

(25) K.Yamazaki, S.Watanabe,``Singularities in mixture models and upper bounds of stochastic complexity." International Journal of Neural Networks, Vol.16, No.7, pp.1029-1038,2003.

(26) K.Yamazaki, S.Watanabe,`` Singularities in Complete bipartite graph-type Boltzmann machines and upper bounds of stochastic complexities", IEEE Trans. on Neural Networks, Vol. 16 (2), pp 312-324, 2005.

(28) S.Watanabe, K.Fukumizu,K.Hagiwara, S.Amari,``Learning Theory of Singular Statistical Models," "Vol.J88-D2 No.2 pp.159-169,2005.(Survay Paper).

(28) K. Yamazaki and S. Watanabe, "Algebraic geometry and stochastic complexity of hidden Markov models", Neurocomputing,Vol.69,pp.62-84,2005.

(29) S.Watanabe,``Algebraic geometry of singular learning machines and symmetry of generalization and training errors," Neurocomputing, Vol.67,pp.198-213,2005.

(30) M.Aoyagi, S.Watanabe,``Stochastic complexities of reduced rank regression in Bayesian estimation," Neural Networks, Vol.18,No.7,pp.924-933,2005.

(31) K.Nagata, S.Watanabe,``A method to estimate the generalization error of singular learning machines by decomposition of Kullback information," Vol.J88-II, No.6, pp.994-1002,2005.

(32) N. Nakano, K.Takahashi, S.Watanabe,``A method to estimate the efficiency of Markov chain Monte Carlo in singular learning machines," Vol.J88-D-II,No.10,pp.2011-2020,2005.

(33) M.Aoyagi,S.Watanabe,``Resolution of singularities and generalization error with Bayesian estimation for layered neural network," Vol.J88-D-II,No.10,pp.2112-2124,2005.

(34) S.Nakajima,S.Watanabe,``Generalization performance of subspace Bayes approach in linear neural networks, " to appear in IEICE Transactions (A).

(35) T.Hosino, K.Watanabe,S.Watanabe,``Stochastic complexity of Hidden Markov Models on the Variational Bayesian Learning," to appear in IEICE Transactions (D-II).

(1) M.Yoneyama, S.Watanabe, H.Kitagawa, T.Okamoto, T.Morita, gNeural Network Recognizing 3-Diminsional Object Through Ultrasonic Scattering Wavesh, Proc. of IEEE Ultrasonics Symp., (Chicago), pp.595-598, 1988.

(2) S.Watanabe, M.Yoneyama, gThe Ultrasonic Robot Eye System Using Neural Network, hProc. of 13th Intern. Cong. on Acoustics, (Belgrade), pp.91-95, 1989.

(3) S.Watanabe, M.Yoneyama, gAn Ultrasonic Robot Eye for Object Recognition Using Neural Network,h Proc. IEEE Ultrason. Symp., (Montreal), pp.1083-1086, 1989.

(4) S.Watanabe, M.Yoneyama, gAn Ultrasonic Robot Eye for Three-Dimensional Object Recognition Using Neural Networkh, Proc. of EUSIPCO-90, (Barcelona), pp.1687-1690, 1990.

(5) S.Watanabe, M.Yoneyama, gThree-Dimensional Object Recognition System Combining Acoustical Imaging with Neural Networkh, Proc. of ISITA-90, (Honolulu), pp.655-658, 1990.

(6) S.Watanabe, M.Yoeneyama, gAn Ultrasonic Robot Eye System for Three-dimensional Object Recognition Using Neural Network,h Proc. of IEEE Ultrasonics Symp., (Honolulu), pp.351-354, 1990.

(7) S.Watanabe, H.Watanabe, A.Saitou. M.Yoneyama, gAn Application of Neural Networks to an Ultrasonic 3-D Visual Sensorh, Proc. of IJCNN, pp.1397 -1402, (Singapole) 1991.

(8) S.Watanabe, M.Yoneyama, gA 3-D Visual Sensor Using Neural Networks and Its Application for Factory Automation,h Proc. of FENDT91, (Seoul), pp.379-386, 1991.

(9) S.Watanabe, M.Yoneyama, gAn Ultrasonic Visual Sensor Using a Neural Network and Its Application for Automatic Object Recognition,h IEEE Ultrasonics Symp. (Florida) pp.781-784, 1991.

(10) S.Watanabe, K.Fukumizu, gThe Unified Neural Network Theory and Proposal of New models,h 2nd Int. conf. on Fuzzy logic and Neural Networks, (Iizuka) pp.725-728, 1992.

(11) S.Watanabe, M.Yoneyama, gAn Ultrasonic Robot Eye Using Neural Networks, hAcoustical Imaging, Plrenum Press, New York, Vol.18, pp.83-95, 1992.

(12) K.Takatsu, S.Watanabe, H.Sawai, M.Yoneyama, gA Proposal of image restoration using Genetic Algorithms,h Proc. of IJCNN (Beijing), Vol.1, pp.642-647, 1992.

(13) S.Watanabe, K.Fukumizu, gThe Unified Neural Network Theory and Its Application to New Models,h Proc. of IJCNN (Beijing), Vol.2, pp.381-386, 1992.

(14) S.Watanabe, M.Yoneyama, gAn Ultrasonic 3-D Object Recognition Method Based on the Unified Neural Network Theory,h Proc. of IEEE US Symp. (Tucson, Arizona), pp.1191-1194, 1992.

(15) S.Watanabe, M.Yoneyama, S. Ueha, gAn ultrasonic 3-D object identification system combining ultrasonic imaging with a probability competition neural network,hProc. of Ultrasonics International 93 conference, (Vienna), pp.767-770, 1993.

(16) S.Watanabe, gDifferential equations accompanying neural networks and solvable nonlinear learning machines,h Proc. of IJCNN (Nagoya), pp.2968-2971, 1993.

(17) K.Fukumizu, S.Watanabe, gProbability density estimation by regularization method,h Proc. of IJCNN (Nagoya), pp.1727-1730, 1993.

(18) S.Ishii, K.Fukumizu, S.Watanabe, gAssociative memory using spatiotemporal chaos,h Proc. of IJCNN (Nagoya), pp.2638-2641, 1993.

(19) S.Ishii, K. Fukumizu, S.Watanabe, gGlobally coupled map model for information processing,hProc. of International Symp., on Nonlinear Theory and Its Applications, (Honolulu),pp.1157-1160, 1993.

(20) K.Fukumizu, S.Watanabe, gError estimation and learning data arrangement for neural networks,h proc. of IEEE world congress on computational intelligence, (Florida), Vol.2 pp.777-780, 1994.

(21) S.Watanabe, gSolvable models of artificial neural networks,h Advances in Neural Information Processing Systems, Morgan Kaufmann, New York, Vol.6, pp.423-430, 1994.

(22) S.Watanabe, M.Yoneyama, gA 3-D Object Classification Method Combining Acoustical Imaging with Probability Competition Neural Networks,hAcoustical Imaging, Plenum Press, New York, Vol.20, pp.65-72, 1994.

(23) S.Watanabe, gAn optimization method of artificial neural networks based on the modified information criterion,h Advances in Neural Information Processing Systems, Morgan Kaufmann, New York, Vol.6, pp.293-300, 1994.

(24) S.Watanabe, gA generalized Bayesian framework for neural networks with singular Fisher information matrices,h Proc. of International Symposium on Nonlinear Theory and Its applications, (Las Vegas), pp.207-210, 1995.

(25) S.Watanabe, M.Yoneyama, gA nonlinear ultrasonic imaging method based on the modified information criterion,h Acoustical Imaging, Vol.22, Plenum Press, New York, pp.549-554, 1996.

(26) S.Watanabe, gOn the essential difference between neural networks and regular statistical models,h Proc. of Int. Conf. on Computational Intelligence and Neuroscience, Vol.2, pp.149-152, 1997.

(27) S.Watanabe, gRealizable approximation bounds for a solvable neural network,hApproximation Theory, Vol.1, Vanderbilt University Press, pp.347-354, 1998.

(28) S.Watanabe, gInequalities of Generalization Errors for Layered Neural Networks in Bayesian Learning,h Proc. of Int. Conf. on Neural Information Processing, pp.59-62, 1998.

(29) S.Watanabe, gApproximation bounds for layered learning machines and environmental probability measures,h Proc. of Int. Conf. on Computational Intelligence and Neuroscience, Vol.2, pp.135-138, 1998.

(30) S.Watanabe, gAlgebraic analysis for neural network learning,h Proc. of IEEE Systems, Man and Cybernetics, (CD ROM) 1999.

(31) S.Watanabe, gAlgebraic analysis for singular statistical estimation,h Proc. of International Journal of Algorithmic Learning Theory, Lecture Notes on Computer Sciences, 1720, pp.39-50, 1999.

(32) S. Watanabe, gMathematical foundation for redundant statistical estimation,h Proc. of the 31th ISCIE International Symposium on Stochastic Systems Theory and Its Applications, Yokohama, pp.119-124, 1999.

(33) S.Watanabe, gAlgebraic analysis for non-regular learning machines,hAdvances in Neural Information Processing Systems, (Denver, USA), 12, pp.356-362, 2000.

(34) S. Watanabe, gAlgebraic geometry of statistical models with singular Fisher metrics,h Proc. of second International Symposium on Frontiers of Time Series Modeling, (Nara) , pp.228-229, 2000.

(35) S. Watanabe, gAlgebraic geometry of free energy in machine learning,h Proc. of Workshop on statistical-Mechanical Approach to Intelligent Information Processing (Sendai), pp.17, 2000.

(36) S. Watanabe, gAlgebraic information geometry for learning machines with singularities,hAdvances in Neural Information Processing Systems, (Denver, USA), pp.329-336. 2001.

(37) Sumio Watanabe, "Bayes and Gibbs Estimations, Empirical Processes, and Resolution of Singularities," Frontiers in Artificial Intelligence and Applications, (Osaka, Japan), Vol.69, No.2, pp.1585-1589, 2001.

(38) Sumio Watanabe, "Resolution of Singularities and Weak Convergence of Bayesian Stochastic Complexity," Singular Models and Geometric Methods in Statistics, (Tokyo, Japan), 156-165, 2002.

(39) Keisuke Yamazaki, Sumio Watanabe, "Resolution of Singularities in Mixture Models and its Stochastic Complexity," Proceedings of the 9th International Conference on Neural Information Processing, (Singapole), CD-ROM, 2002.

(40) Sumio Watanabe, Shun-ichi Amari, "Singularities in Neural Networks Make Bayes Generalization Errors Smaller Even If They Do Not Contain the True," Proceedings of the 9th International Conference on Neural Information Processing,(Singapole), CD-ROM, 2002.

(41) Sumio Watanabe, Shun-ichi Amari, "The effect of singularities in a learning machine when the true parameters do not lie on such singularities," Advances in Neural Information Processing Systems,(Vancouver, CANADA), Vol.15, CD-ROM, 2003.

(42) Keisuke Yamazaki, Sumio Watanabe, "Stochastic complexity of Bayesian networks," Uncertainty in Artificial Intelligence, (Acapulco, Mexico), pp.592-599,2003.

(43) Keisuke Yamazaki, Sumio Watanabe,"Stochastic complexities of hidden Markov models," Neural Networks for Signal Processing XIII,(Toulouse, France), pp.179-188,2003.

(44) Sumio Watanabe, Keisuke Yamazaki, "Algebraic geometry, zeta functions, and marginal likelihood of Bayesian statistics," Anniversary of the information criterion, (Yokohama, Japan), CD-ROM, 2003.

(45) Miki Aoyagi, Sumio Watanabe, ``The generalization error of reduced rank regression in Bayesian estimation," International Symposium on Information Theory and its Applications,CD-ROM, (Parma, Italy),2004.

(46) Keisuke Yamazaki, Sumio Watanabe, ``Newton diagram and stochastic complexity in mixture of binomial distributions, " Lecture Notes in Computer Science, Vol.3244, Proceedings of Algorithmic Learning Theory, (Padova,Italy), pp.350-364,2004.

(47) Kazuho Watanabe, Sumio Watanabe, ``Estimation of the Data region using Extreme-value distributions," Lecture Notes in Computer Science, Vol.3244, Proceedings of Algorithmic Learning Theory, (Padova, Italy), pp.206-220,2004.

(48) K.Watanabe, S.Watanabe, "Lower bounds of stochastic complexities in variational bayes learning of gaussian mixture models," Proceedings of IEEE International Conference on Cybernetics and Intelligent Systems, (Singapore), pp.99-104, 2004.

(49) K.Watanabe, S.Watanabe, "Learning method of the data region based on extreme-value theory," Proceedings of International Symposium on Information Theory and its Applications (Parma, Italy), pp.87-92, 2004.

(50) K. Yamazaki, M. Aoyagi, S. Watanabe, "Stochastic Complexity and Newton Diagram," International Symposium on Information Theory and its Applications,(Parma, Italy), CD-ROM, 2004.

(51) S. Nakajima, S. Watanabe, "Simulation Data Generation from Extended EGA Model and Optimization of Alignment Strategy for Lithography," Proceedings of International Symposium on Information Theory and its Applications, (Parma, Italy), pp.627-632, October, 2004.

(52) T. Hosino, K. Watanabe, S.Watanabe, ``"Stochastic Complexity of Variational Bayesian Hidden Markov Models, " Proc. of IJCNN, CD-ROM, (Motreal, Canada), USA, 2005.

(53) K. Yamazaki, S. Watanabe, "Generalization Errors in Estimation of Stochastic Context-Free Grammar" The IASTED International Conference on Artificial Intelligence and Soft Computing (Benidorm, Spain), pp. 183-188, 2005.

(54) K. Yamazaki, K. Nagata, S. Watanabe, "A New Method of Model Selection Based on Learning Coefficient" Proc. of International Symposium on Nonlinear Theory and its Applications, (Bruge, Belgium) 2005.

(55) S. Nakajima, S.Watanabe, ``Generalization Error of Linear Neural Networks in an Empirical Bayes Approach," Proc. of IJCAI2005(Edinburgh, U.K.), CD-ROM, 2005.

(56) S. Nakajima, S.Watanabe, ``Generalization Error and Free Energy of Linear Neural Networks in Variational Bayes Approach," Proc. of ICONIP2005 (Taipei, Taiwan), 2005.

(57) Kenji Nagata, Sumio Watanabe, 2"A Method to Approximate the Baysian Posterior Distribution in Singular Learning Machines" Proc. of ICONIP2005 (Taipei, Taiwan), 2005.

(58) K.Watanabe, S.Watanabe, ``Variational Bayesian Algorithm and Stochastic Complexity for Mixture Models". Proc. of ICONIP2005 (Taipei, Taiwan), 2005.

(59) K.Watanabe, S.Watanabe, ``Stochastic complexity for mixture of exponential families in variational bayes" Proc. of ALT2005 (Singapore),2005.

(60) K.Watanabe, S.Watanabe, "On Variational Bayes Algorithms for Exponential Family Mixtures". International Symposium on Nonlinear Theory and its Applications (Bruge, Belgium), 2005.

(61) K. Watanabe, S.Watanabe, ``Variational Bayesian Stochastic Complexity of Mixture Models," Proc. of Advances in Neural Information Processing Systems, 2006.

(62) M.Aoyagi, S.Watanabe,``The zeta function for learning theory and resolution of singularities," Proc. of ISAAC, 2005.

Japanese Names of Articles .