JapanesebHomebOur Group | NTT CS Labs.
Naonori Ueda
Director, PhD
NTT CS-Labs.

Guest Professor of Nara Advanced Institute of Science and Technology
Guest Professor of National Institute of Informatics

Biography

Naonori Ueda received the B.S., M.S., and Ph D degrees in Communication Engineering from Osaka University, Osaka, Japan, in 1982, 1984, and 1992, respectively. In 1984, he joined the Electrical Communication Laboratories, NTT, Japan, where he was engaged in research on image processing, pattern recognition, and computer vision. In 1991, he joined the NTT Communication Science Laboratories, where he has invented a significant learning principle for optimal vector quantizer design and has developed some novel learning algorithms including deterministic annealing EM (DAEM) algorithm, ensemble learning, the split and merge EM (SMEM) algorithm, semi-supervised learning, variational Bayesian model search algorithm for mixture models and its application to speech recognition, and probabilistic generative models for multi-labeled text in WWW. His current research interests include parametric and non-parametric Bayesian approach to machine learning, pattern recognition, data mining, signal processing, and cyber-physical systems. From 1993 to 1994, he was a visiting scholar at Purdue University, West Lafayette, USA. Currently, he is a director of NTT Communication Science Laboratories. He is an associate editor of Neurocomputing and Journal of Neural Networks, and is a member of the Institute of Electronics, Information, and Communication Engineers (IEICE), and IEEE.

Awards

Professional Activities

Invited Academic Talks

Career

Publications

Refereed Journal Papers

  1. K. Ishiguro, T. Iwata, and N. Ueda,"Dynamic infinite relational model for time-dependent relational data analysis",Journal of Information Processing Society of Japan, Vol. 3, No.1, 1-12, 2010 (in Japanese)

  2. Tomoharu Iwata, Toshiyuki Tanaka, Takeshi Yamada, Naonori Ueda,"Model Learning when Distributions Differ over Time,"Transactions of IEICEJ, Vol.J92-D, No.3, 361-370, 2009 (in Japanese)

  3. Tomoharu Iwata, Takeshi Yamada, Naonori Ueda,"Visualizing Documents based on Topic Models,"Journal of Information Processing Society of Japan, Vol.50, No.6,1649-1659, 2009 (in Japanese)

  4. Kawamae, N., Sakano, H., Yamada, T., and Ueda, N.,"Collaborative filtering focusing on the dynamics and precedence of user preference",Transactions of IEICEJ, (D-II), Vol. J92-DII, No.6, pp. 767-776, 2009, (in Japanese)

  5. Fujino, A., Ueda, N., and Saito, K. (2008). Semisupervised learning for a hybrid generative/discriminative classifier based on the maximum entropy principle. IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 30(3), 424-437. [IEEE Xplore] [DOI link] [IEEE Copyright Notice]

  6. Ueda N, Yamada T and Kuwata S, "Co-clustering Discrete Data Based on the Dirichlet Process Mixture Model", Transaction of Information Processing Society of Japan, Vol.1 No.1 (pp. 60-73), (2008), [Transaction of Information Processing Society of Japan],(in Japanese)

  7. Iwata, T.,Yamada, T.,and Ueda, N.,:"Collaborative filtering efficiently using purchase orders" Transaction of Information Processing Society of Japan, Vo.49, No.SIG4 (TOM20), pp. 125-134, 2008, (in Japanese).

  8. Naud A, Usui S, Ueda N and Taniguchi T, "Visualization of documents and concepts in Neuroinformatics with the 3D-SE Viewer", Neuroinformatics, 2007.

  9. Kuwata S, Ueda N, "One-shot Collaborative Filtering" Transaction of Information Processing Society of Japan, Vol.48, No.SIG_15(TOM_18), pp. 153-162, 2007, [Transaction of Information Processing Society of Japan], (in Japanese)

  10. Kawamae, N., Yamada, T. and Ueda, N.,"Personalized Ranking by Identifying, RelativeInnovators", FIT2007 Letters, Vol.6, pp.99-102, 2007.

  11. Kuwata, S., and Ueda, N.,"An efficient collaborative filtering algorithm based on marginal rating distributions," International Journal of IT & IC, IEEE CIS, Vol.2, No.1, 2007.

  12. Fujino A., Ueda, N and Saito K, "Semi-supervised Learning of Multi-class Classifiers for Multi-component Data" Transaction of Information Processing Society of Japan, Vol.48, No.SIG_15(TOM_18), pp. 163-175, 2007, [Transactions of IPSJ.], (in Japanese)

  13. Fujino, A., Ueda, N., and Saito, K., "A hybrid generative/discriminative approach to text classification with additional information", Information Processing & Management, Elisevier, Vol.43, pp. 379-392, 2007.

  14. Usui,S.,Plames,P.,Nagata,K.,Taniguchi,T.,and Ueda,N., "Keyword extraction, ranking, and organization for the neuroinfomatics platform," Biosystems, Elsevier Science, Vol.88, Issue 3, pp. 334-342, 2007, [Biosystems].

  15. Iwata,T., Saito,K., Ueda,N, Stromsten,S,Griffiths,T., and Tenenbaum J., "Parametric Embedding for Class Visualization", Neural Computation Vol. 19, No. 9, pp. 2536-2556: 2536-2556, 2007.

  16. Kawamae, N., Yamada, T. and Ueda, N.,"Personalized Ranking by Identifying, RelativeInnovators", FIT2007 Letters, Vol.6, pp.99-102, 2007.

  17. Ueda, N., and Yamada, T., "Nonparametric Bayes," Journal of Japanese Applied Mathematics Vol.17, No.3, pp.196-214, 2007.

  18. Fujino A.,Ueda,N and Saito,K. "Text Classification by Effectively Using Additional Information Based on Maximum Entropy Principle(Information Retrieval)" Transaction of Information Processing Society of Japan, Vol.47, No.10, pp. 2929-2937, 2006, [ Transactions of IPSJ.], (in Japanese).

  19. Fujino, A., Ueda, N., and Saito, K."A hybrid generative/discriminative classifier design for semi-supervised learning", Journal of JSAICVol.21, No.3, pp.301-309, 2006, (in Japanese).

  20. Kimura, M., Saito, K., and Ueda, N., "Modeling network growth with directional attachment and communities," Systems and Computers in Japan, Vol. 35, No. 8, pp. 1-11, 2004, [Systems and Computers in Japan].

  21. Ueda, N. and Saito, K., "Parametric mixture models for multi-topic text," Systems and Computers in Japan, Vol.37, No.2, pp. 56-66, 2006, [Systems and Computers in Japan]

  22. Ueda, N., "Ensemble Learning," Transactions of IPSJ, CVIM-1036, (invited) Vol.46, No.SIG15(CVIM 12), pp. 11-20, 2005, [Transaction of Information Processing Society of Japan], (in Japanese)

  23. Iwata,T., Saito,K., Ueda,N., Stromsten,S,Griffiths,T., and Tenenbaum J., "Parametric Embedding for Class Visualization, " Neural Computation, vol.46,no.9, pp. 2337-2346, 2005, (in Japanese).

  24. Fujino, A., Ueda, N., and Saito, K.., "Semi-supervised learning on hybrid generative/discriminative models," FIT2005 Letters, 2005, (in Japanese).

  25. Iwata, T., Saito, K., and Ueda, N., "Visualization via posterior preserving embedding "FIT2004 Letters, Vol. 3, pp. 119-120, 2004, (in Japanese).

  26. Kaneda, Y., Saito, K., and Ueda, N., "Automatic extraction of correspondences between document taxonomies," FIT2004 Letters, Vol. 3, pp.121-122, 2004, (in Japanese).

  27. Kaneda, Y., Ueda, N., "A Robust text data clustering method for high-dimensional data," FIT2004 Letters, Vol. 3, pp. 123-124, 2004, (in Japanese).

  28. Fujino., A., Ueda, N., and Saito, K.., "Relevance feedback with cross validation," FIT2004, Vol. 3, pp. 53-54, 2004, (in Japanese).

  29. Kimura, M., Saito, K., and Ueda, N, "Modeling share dynamics by extracting competition structure", Physica D, Vol.198, pp. 51-73, 2004.

  30. Watanabe, S., Minami, Y., Nakamura, A., and Ueda, N., "Variational Bayesian Estimation and Clustering for Speech Recognition", IEEE transaction on Speech and Audio Processing, Vol. 12, pp. 365-381, 2004.

  31. Ueda, N., and Inoue, M., "Extended Tied-Mixture HMMs for Both Labeled and Unlabeled Time Series Data", Journal of VLSI Signal Processing, pp. 189-197, 2004.

  32. Kimura, M., Saito, K., and Ueda, N, "Modeling of growing networks with directional attachment and communities", Neural Networks, Vol. 17, No. 7, pp. 975-988, 2004.

  33. Ueda, N, and Saito, K. " Parametric Mixture Models for Multi-Topic Text", Transactions of IEICEJ, (D-II), Vol. J87-DII, No.3, pp. 872-883, 2004, (in Japanese)

  34. Ueda, N. and Inoue, M., "Extended tied-mixture HMMs for both labeled and unlabeled time series data," to appear Journal of VLSI Signal Processing Systems,Vol. 37, pp. 189-197, 2004.

  35. Kimura, M., Saito, K., and Ueda, N, "Modeling of growing networks with directional attachment and communities," Transactions of IEICEJ, Vol. J86-DII, No, 10, pp. 1468-1479, 2003, (in Japanese).

  36. Ueda, N. and Saito, K., "Multi - topic Text Model for Topic - based Text Retrieval" Transaction of Information Processing Society of Japan Vol. 44, No. SIG14(TOM9), pp. 1-8, 2003,[Transaction of Information Processing Society of Japan] (in Japanese).

  37. Yamada, T., Saito, K., and Ueda. N., "Embedding networks data based on cross-entropy minimization," Transaction of Information Processing Society of Japan Vol. 44, No. 9, pp. 2401-2408, 2003, [Transaction of Information Processing Society of Japan] (in Japanese).

  38. Inoue, M. and Ueda, N., "Exploitation of unlabeled sequences in hidden markov models" IEEE Transaction on Pattern Analysis and Machine Intelligence (PAMI), Vol. 25, No. 12, pp1570-1581, 2003.

  39. Watanabe, S., Minami, Y., Nakamura, A., and Ueda, N., "Selection of Shared-States Hidden Markov Model Structure Using Bayesian Criterion," Transactions of IEICEJ, Vol. J86-DII, No. 6, pp. 776-786, 2003, (in Japanese).

  40. Ueda, N. and Ghahramani Z., "Bayesian model search for mixture models based on optimizing variational bounds," Neural Networks, Vol.15, pp. 1223-1241, 2002.

  41. Inoue, M. and Ueda, N., "Use of Unlabeled Time Series Data in Hidden Markov Models" Transactions of IEICEJ, Vol. J86-DII, No. 2, pp. 173-183, 2003 (in Japanese).

  42. Ueda, N., "Variational Bayesian Learning for Optimal Model Search" Journal of Japanese Society for Artificial Intelligence, Vol.16, No.2, 2001, (in Japanese).

  43. Suzuki, S., and Ueda, N., "Adaptive clustering method using modular learning architecture," Transactions of IEICEJ, Vol. J83_DII, No. 6, pp. 1529-1538, 2000, (in Japanese).

  44. Ueda, N., "EM algorithm with split and merge operations for mixture models (invited)," Transactions of IEICE, Vol. E83-D, No. 12, pp. 2047-2055, 2000.

  45. Suzuki, S., and Ueda, N., "Adaptive clustering method using modular learning architecture," Transactions of IEICEJ, Vol. J83_DII, No. 6, pp. 1529-1538, 2000, (in Japanese).

  46. Ueda, N., Nakano, R., Ghahramani, Z., and Hinton, G. E.,"SMEM Algorithm for Mixture Models," Neural Computation, Vol. 12, No. 9, pp. 2109-2128, 2000.

  47. Ueda, N., Nakano, R., Ghahramani, Z., and Hinton, G. E.,"Split and merge EM algorithm for improving Gaussian mixture density estimates (invited)," Journal of VLSI Signal Processing, Vol. 26, pp. 133-140, 2000.

  48. Ueda, N., "Optimal Linear Combination of Neural Networks for Improving Classification Performance," IEEE Transactions on Pattern Analysis and Machine Intelligence (PAMI). Vol. 22, No.2, pp. 207-215, 2000.

  49. Ueda, N. and Nakano, R., "Probabilistic Mixture Subspace Method," Transactions of IEICE, Transactions of IEICEJ, Vol. J82-DII, No. 12, pp. 2394-2401, 1999, (in Japanese).

  50. Ueda, N. and Nakano, R., "EM Algorithm with Split and Merge Operations for Mixture Models," Transactions of IEICE, Transactions of IEICEJ, Vol. J82-DII, No. 5, pp. 930-940, 1999, (in Japanese).

  51. Ueda, N., "Optimum Linear Combination of Neural Network Classifiers Based on the Minimum Classification Error Criterion," Transactions of IEICEJ, Vol. J82_DII, No. 3, pp. 522-530, 1999, (in Japanese).

  52. Ueda, N. and Nakano, R., "Deterministic Annealing EM Algorithm," Neural Networks, Vol. 11, No. 2, pp. 271-282, (1998).

  53. Ueda, N. and Nakano, R., "Analysis of Generalization Error on Ensemble Learning," Transactions of IEICEJ, Vol. J80-DII, No. 9, pp. 2512-2521, 1997, (in Japanese).

  54. Ueda, N. and Nakano, R., "Deteministic Anneling EM Algorithm," Transactions of IEICEJ, Vol. J80-DII, No. 1, pp. 267-276, 1997, (in Japanese).

  55. Ueda, N. and Mase, K., "Tracking Moving Contours Using Energy-minimizing Elastic Contour Models," International Journal of Pattern Recognition and Artificial Intelligence, Vol. 9, No. 3, pp. 465-484, 1995.

  56. Ueda, N. and Nakano, R., "A New Competitive Learning Approach Based on an Equidistortion Principle for Designing Optimal Vector Quantizers,"Neural Networks, Vol.7, No.8, pp. 1211-1227, 1994.

  57. Ueda, N. and Nakano, R., "Competitive and Selective Learning method for Vector Quantizer Design - Equidistortion Principle and Its Algorithm -,"Transactions of IEICEJ, Vol. J77-DII, No. 11, pp. 2265-2278, 1994, (in Japanese).

  58. Ueda, N. and Suzuki, S., "Learning Visual Models from Shape Contours Using Multiscale Convex/Concave Structure Matching," IEEE Transactions on Pattern Analysis and Machine Intelligence (PAMI), Vol. 15, No. 4, pp. 337-352, 1993, [ IEEE Transactions on Pattern Analysis and Machine Intelligence (PAMI).

  59. Suzuki, S., Ueda, N. and Sklansky, J., "Graph-Based Thinning for Binary Images," International Journal of Pattern Recognition and Artificial Intelligence, Vol. 7, No. 5 pp. 1009-1030, 1993.

  60. Ueda, N., Mase K., and Suenaga Y., "A Contour Tracking Method Using Elastic Contour Model and Energy Minimization Approach," Transactions of IEICEJ, Vol. J75-DII, No. 1, pp. 111-120, 1992, (in Japanese).

  61. Ueda, N. and Suzuki, S., "Automatic Shape Model Acquisition Based on A Generalization of Convex/Concave Structure," Transactions of IEICEJ, Vol. J74-DII, No. 2, pp. 220-229, 1991, (in Japanese).

  62. Ueda, N. and Suzuki, S., "A Deformed Line-Drawing Matching Algorithm Using Multiscale Convex/Concave Structures," Transactions of IEICEJ, Vol. J73-DII, No. 7, pp. 992-1000, 1990, (in Japanese).

  63. Ueda, N., Nagura, M., Kosugi, M., and Mori, K., "Image Enhancemen Method for Law Quality Drawings," Transactions of the Institute of Television Engineers of Japan, Vol. 42, No. 8, pp. 831-836, 1988, (in Japanese).

IEEE Copyright Notice

©2008 IEEE. Personal use of this material is permitted. However, permission to reprint/republish this material for advertising or promotional purposed or for creating new collective works for resale or redistribution to servers or lists, or to reuse any copyrighted component of this work in other works must be obtained from the IEEE.

These materials are presented to ensure timely dissemination of scholarly and technical work. Copyright and all rights therein are retained by authors or by other copyright holders. All persons copying this information are expected to ashere to the terms and constraints invoked by each author's copyright. In most cases, these works may not be reposted without the explicit permission of the copyright holder.

Refereed International Conference Papers

  1. Shiro Usui, Nilton L. Kamiji, Tatsuki Taniguchi, Naonori Ueda, "RAST: A Related Abstract Search Tool," International Conference on Neural Information Processing (ICONIP) 2009.

  2. Tomoharu Iwata, Takeshi Yamada, Naonori Ueda, "Modeling Social Annotation Data with Content Relevance using a TopicModel,"Advances in Neural Information Processing Systems (NIPS2009), 835-843, 2009

  3. Tomoharu Iwata, Shinji Watanabe, Takeshi Yamada, Naonori Ueda,"Topic Tracking Model for Analyzing Consumer Purchase Behavior,"Proc. of 21st International Joint Conference on Artificial Intelligence(IJCAI-09), 1427-1432, 2009

  4. Tomoharu Iwata, Takeshi Yamada, Naonori Ueda, "Probabilistic Latent Semantic Visualization: Topic Model for Visualizing Documents," Proc. of 14th ACM SIGKDD International Conference on Knowledge Discovery and Data Minig (KDD2008), pp.363-371, 2008.

  5. Ishiguro, K., Yamada, T. and Ueda, N, "Simultaneous Clustering and Tracking Unknown Number of Objects", Proc. of the 19th IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR08), pp. 1-8, 2008, [CVPR08]

  6. Usui S, Naud A, Ueda N and Taniguchi T, "3D-SE Viewer: A Text Mining Tool based on Bipartite Graph Visualization", 20th International Joint Conference on Neural Networks (IJCNN'07), 2007.

  7. Kuwata S. and Ueda N., "One-shot Collaborative Filtering," IEEE CIDM2007, Vol.1, No.1, pp.300-307, 2007.

  8. Fujino A., Ueda N., and Saito K., "Semi-supervized learning for multi-component data classification," to appear in Proc. of International Joint Conference on Areificial Intelligence (IJCAI2007),2007.

  9. Kuwata S. and Ueda N., "One-shot collaborative filtering," to appear in Pro. of IEEE Symposium on Compututational Intelligence and Data Mining (CIDM2007), 2007.

  10. Kemp C., Tenenbaum J. B., Griffiths T.L.., Yamada T. and Ueda N., "Learning systems of concepts with an infinite relational model," Proc. of the 21st National Conference on Artificial Intelligence(AAAI-06), 2006

  11. Iwata T., Saito K., and Ueda N., "Visual nonlinear discriminant analysis for classifier design," Proc. of the 14th European Symposium on Artificial Neural Networks (ESANN2006),pp.283-288, 2006.

  12. Usui S., Palmes P., Nagata K., Taniguchi T. and Ueda N, "Extracting keywords from research abstracts for the neuroinformatics platform index tree," To appear in Proc. of International Joint Conference on Neural Networks (IJCNN2006), 2006.

  13. Ueda N., "Bayesian probabilistic models for data partitioning and their applications," Proc. of the 17th International Symposium on Mathematical Theory of Networks and Systems (MTNS2006), 2006.

  14. Saito K.. and Ueda N., "Filtering Search Engine Spam based on Anomaly Detection Approach," Proc. of the KDD2005 Workshop on Data Mining Methods for Anomaly Detection, pp.62-67, 2005.

  15. Usui S., Palmes P., Nagata K., Taniguchi T. and Ueda N., "Relevance keyword extraction, ranking, and organization for the neuroinformatics platform, Proc. of International Conference on Biological Computation," Proc. of BIOCOMP, 2005.

  16. Fujino A.., Ueda N., and Saito K., "A Classifier design based on combining multiple components by maximum entropy principle," Proc. of the 2nd Asia Information Retrieval Symposium (AIRS2005), 2005.

  17. Kimura M., Saito K., and Ueda N., "Multinomial PCA for extracting major latent topics from document streams," Proc. of IJCNN, 2005.

  18. Fujino A.., Ueda N. and Saito K.., "A hybrid generative/discriminative approach to semi-supervised classifier design," Proc. of the 20th National Conference on Artificial Intelligence (AAAI-05), pp. 764-769, 2005.

  19. Inoue M. and Ueda N., "Retrieving lightly annotated images using image similarities," ACM Symposium on Applied Computing (SAC), Special Track on Information Access and Retrieval (IAR)Santa Fe, March 14-17, pp.1031-1037, 2005

  20. Iwata T, Saito K, Ueda N, Stromsten S, Thomas L. Griffiths, Joshua B. Tenenbaum, "Parametric Embedding for Class Visualization, " Advances in Neural Information Processing Systems 17 (NIPS2004), pp. 617-624, 2005

  21. Kimura M., Saito K. and Ueda N., "Modeling share dynamics by extracting competition structure," Proc. of the 5th International Conference on Complex Systems, p. 72, 2004.

  22. Kaneda Y., Ueda N. and Saito, K., "Extended Parametric Mixture Model for Robust Multi-labeled Text Categorization," Proc. of the 8-th International Conference on Knowledge-Based Intelligent Information & Engineering Systems, Vol. 3214 of Lecture Notes in Computer Science, pp. 616-623, 2004.

  23. Ueda N., and Saito K., "Simplex mixture models for multi-topic text," In Science of Modeling, ISM Report on Research and Education No.17, The Institute of Statisitical Mathematics, pp. 380-381, 2003.

  24. Kimura M., Saito K. and Ueda N., "Modeling share dynamics by extracting competition structure," In Science of Modeling, ISM Report on Research and Education No.17, The Institute of Statisitical Mathematics, pp.366-367, 2003.

  25. Yamada T., Saito K and Ueda N, "Cross-entropy based embedding for relational data," International Conference on Machine Learning (ICML2003), pp. 832-839, 2003.

  26. Watanabe S., Minami Y., Nakamura A., and Ueda N., "Bayesian acoustic modeling for spontaneous speech recognition," IEEE Workshop on Spontaneous Speech Processing and Recognition (SSPR03), pp. 47-50, 2003.

  27. Watanabe S., Minami Y., Nakamura A., and Ueda N., "Application of variational bayesian estimation and clustering to acoustic model adaptation," IEEE International Conference on Acoustic, Speech, and Signal Processing (ICASSP03), Vol. 1, pp. 568-571, 2003.

  28. Kimura M., Saito K., and Ueda N., "Modeling of growing networks with directional attachment and communities," European Symposium on Artificial Neural Networks (ESANN03), pp. 15-20, 2003.

  29. Kimura M., Saito K., and Ueda N., "Modeling of growing networks with communities," IEEE International Workshop on Neural Networks for Signal Processing (NNSP2002), pp. 189-198, 2002.

  30. Watanabe S., Minami Y., Nakamura A., and Ueda N., "An application of variational Bayesian approach to speech recognition," to appear Advances in Neural Information Processing Systems 15(NIPS15), MIT Press, pp. 1261-1268, 2002.

  31. Watanabe S., Minami Y., Nakamura A., and Ueda N., "Constructing shared-state HMMs based on a Bayesian approach," International Conference on Spoken Language Processing (ICSLP02), Vol. 4, pp. 2669-2672, 2002.

  32. Ueda N. and Saito K., "Parametric mixture models for multi-topic text," Neural Information Processing Systems 15(NIPS15), MIT Press, pp. 737-744, 2002.

  33. Ueda N. and Saito K., "Singleshot detection of multi-category text using parametric mixture models," ACM SIG Knowledge Discovery and Data Mining (SIGKDD2002), pp. 626-631, 2002.

  34. Inoue M. and Ueda N., " HMMs for both labeled and unlabed time series data," IEEE Neural Networks for Signal Processing (NNSP2001), pp. 93-102, 2001.

  35. Ueda N. and Ghahramani Z., "Optimal model inference for Baysian mixture of experts," IEEE Neural Networks for Signal Processing (NNSP2000), pp. 145-154, 2000.

  36. Ueda N., Nakano R., Ghahramani Z. and Hinton, G. E., "Pattern classification using a mixture of factor analyzers," IEEE Neural Networks for Signal Processing (NNSP99), pp. 525-533, 1999.

  37. Ueda N., Nakano R., Ghahramani Z., and Hinton G. E., "SMEM algorithm for mixture models," Neural Information Processing Systems 11 (NIPS11), pp. 599-605, 1999.

  38. Ueda N., Nakano R., Ghahramani Z. and Hinton G. E., "Split and merge EM algorithm for improving Gaussian mixture density estimates," IEEE Neural Networks for Signal Processing (NNSP98), pp. 274-283, 1998.

  39. Ueda N. and Nakano R., "Combining discriminant-based classifiers using the minimum classification error discrimininant,"IEEE Neural Networks for Signal Processing(NNSP97), pp. 365-374, 1997.

  40. Suzuki S. and Ueda N., "Self-organization of feature columns and its application to object classification," Proceedings of International Conference on Neural Information Processing (ICONIP97), pp. 1166-1169, 1997.

  41. Ueda N. and Nakano R., "Generalization error of ensemble estimators," Proceedings of International Conference on Neural Networks (ICNN96), pp. 90-95, 1996.

  42. Ueda N. and Nakano R., "Deterministic annealing variant of the EM algorithm," Neural Information Processing Systems 7 (NIPS7), MIT Press, Cambridge MA, pp. 545-552, 1995.

  43. Ueda N. and Nakano R., "A new maximum likelihood training and application to probabilistic neural networks," Proceedings of International Conference on Artificial Neural Networks (ICANN95), pp. 497-504, 1995.

  44. Ueda N. and Nakano R., "Estimating expected error rates of neural network classifiers in small sample size situations: A comparison of cross-validation and bootstrap," International Conference on Neural Networks (ICNN95), pp. 101-104, 1995.

  45. Ueda N. and Nakano R., "Mixture density estimation via EM algorithm with deterministic annealing," Proceedings of IEEE Neural Networks for Signal Processing (NNSP94)}, pp. 69-77, 1994.

  46. Ueda N. and Nakano R., "A new learning approach based on equidistortion principle for optimal vector quantizer Design," Proceedings of IEEE Neural Networks for Signal Processing (NNSP93), pp. 362-371, 1993.

  47. Ueda N. and Nakano R., "Competitive and selective learning method for designing optimal vector quantizers," Proceedings of IEEE International Conference on Neural Networks (ICNN93), pp. 1444-1450, 1993.

  48. Ueda N. and Mase K., "Tracking moving contours using energy-minimizing elastic contour models,"Proceedings of European Conference on Computer Vision (ECCV92), pp. 453-457, 1992.

  49. Suzuki S. and Ueda N., "Robust vectorization using graph-based thnning and reliability-based line approximation," Proceedings of IEEE Conference on Computer Vision (CVPR91), pp. 494-500, 1991.

  50. Ueda N. and Suzuki S., "Automatic shape model acquisition using multiscale segment matching," Proceedings of International Conference on Pattern Recognition (ICPR90), pp. 897-902, 1990.

  51. Ogawa H., Kawada E.. and Ueda N., "Application of image processing equipment with multiprocessors to line-drawing recognition," Proceedings of SPIE-845, pp. 97-103, 1987.

  52. Okudaira M., Ueda N. and Aoki U., "Image enhancement of handwritten drawings and their recognition followed by interactive processing," Proceedings of SPIE-707, pp. 42-50, 1986.

Invited Paper

  1. Ueda, N., Nakano, R., "Competitive and selective learning method for vector quantizer design -Equidistortion principle and its algorithm," Systems and computers in Japan, Scripta Technica, Inc., Vol. 26, No. 9, pp. 34-49, 1995.

  2. Ueda, N., Mase, K. and Suenaga, Y., "A contour tracking method using elastic contour model and energy minimizing approach," Systems and computers in Japan, Scripta Technica, Inc., Vol. 24, No. 8, pp. 59-70, 1993.

  3. Ueda, N. and Suzuki, S., "Automatic shape model acquisition based on a generalization of convex/concave structure," Systems and computers in Japan, Scripta Technica, Inc. Vol. 23, No. 1, pp. 89-100, 1992.

  4. Ueda, N. and Suzuki, S., "A matching algorithm of deformed planar curves using multiscale convex/concave structures," Systems and computers in Japan, Scripta Technica, Inc. Vol. 22, No. 5, pp. 94-104, 1991.

Invited Tutorial Papers

  1. Ueda, N., "EM algorithm," Society of Instrument and Control Engineers(SICE), Vol.44, No.5, pp.333-338, 2005. (In Japanese)

  2. Ueda, N., "The goal of Web science research," OHM, Vol.91, No.10,pp.6--7, 2004.(In Japanese)

  3. Ueda, N., "Bayesian Inference Algorithms -Approximation Methods for High-Dimensional Integrals-," Journal of the Japanese Society for Artificial Intelligence, Vol. 19, No. 6, 2004 (in Japanese).

  4. Ueda, N. and Saito, K., "Probablistic Models for Multi-topic Text," Information Processing Society of Japan, Vol. 45, No. 2, 3, 2004 (in Japanese).

  5. Ueda, N., "Probablistic Models and Statistical Learning," Computer Today, No.114, 2003.

  6. Ueda, N., "Bayeaian Learning I - IV," Journal of IEICEJ, Vol. 85, No. 4, 6, 7, 8, 2002 (in Japanse).

  7. Ueda, N., "Ensemble Learning," Journal of the Society of Instrument and Control Engineers, Vol. 41, pp. 248, 2002.

  8. Ueda, N., "The Front of Bayesian Learning -Variational Bayesian Learning, " Information Processing Society of Japan, Vol. 42, No. 1, 2001 (in Japanese).

  9. Ueda, N., "An Inquiry into Statistical Learning Research," Information Processing Society of Japan,, Vol. 41, No. 6, pp. 730-733, 2000 (in Japanese).

  10. Ueda, N. and Nakano, R., "Deterministic Annealing EM Algorithm," Journal of the Society of Instrument and Control Engineers, Vol. 38, No. 7, pp. 444-449, 1999 (in Japanse).

  11. Ueda, N. and Nakano, R., "Deterministic Annealing -Another Type of Annealing-," Journal of Japanese Society for Artificial Intelligence, Vol. 12, No. 5, pp. 689-697, 1997 (in Japanse).

  12. Mase, S. and Ueda, N., "Mathematical Morphology and Image Analysis I," Journal of IEICEJ, Vol. 64, No. 2, pp. 166-174 , 1991 (in Japanese).

  13. Ueda, N. and Mase, S., "Mathematical Morphology and Image Analysis II," Journal of IEICEJ, Vol. 64, No. 3, pp. 271-279, 1991 (in Japanse).

Internal Invited Technical Reports at NTT

  1. Fujino, A., Ueda, N., and Saito, K., "Semi-supervised learning forautomatic text classification, " NTT Technical Journal, Vol.19, No.6, pp.26-28, 2007. (In Japanese)

  2. Ueda, N., "Web Science Research," NTT Technical Review}, Vol. 3, No. 3, pp. 12-14, 2005.

  3. Ueda, N., "Comtemplation to Web science," NTT Technical Journal, Vol.16,No.6, p. 22, 2004. (In Japanese)

  4. Ueda, N., "Web Science Research," NTT Technical Journal, Vol.16, No.6,2004. (In Japanese)

  5. Ueda, N. and Nakano, R., "Competitive and Selective Learning Method for Optimal Vector Quantizer Design," NTT R&D, Vol. 42, No. 6, 1993 (in Japanese).

  6. Nakano, R., Ueda, N., Saito, K., and Yamada, T., " Research on Learning Aiming at Artificial Intelligence," NTT R&D, Vol. 42, No. 9, pp. 1175-1184, 1993 (in Japanese).

  7. Ueda, N., Mase, K., and Suenaga, Y., "Contour Tracking Method Using Energy-minimizing Elastic Models," NTT R&D, Vol. 42, No. 4, pp. 477-486, 1993 (in Japanese).

  8. Ueda, N. and Suzuki, S., "Multiscale Convex/Concave Structure Matching : MC Matching Method," NTT R&D, Vol. 40, No. 3, pp.399-406, 1991 (in Japanese).

  9. Kawada, E, Ueda, N., Ogawa, H., and Kosugi, M., "A Figure Recognition Method for Hand-Written Drawings," NTT Electrical Communications Laboratories Technical Journal, Vol. 37, No. 3, pp. 217-223, 1988 (in Japanese).

  10. Ueda, N., Nagura, M., Hoshino, T., and Mori, K., "Image Enhancement Method for Hand-Written Line Drawings," NTT Electrical Communications Laboratories Technical Journal, Vol. 37, No. 3, pp. 211-216, 1988 (in Japanese).

Book & Book Chapters

  1. Kabashima, Y. and Ueda, N., "Frontier of Statistical Science 11, Computational Statistics I - (3)," Iwanami Shoten, Japan, 2003.(in Japanese)

  2. Ishii, K., Ueda, N., Maeda, E., and Murase, H., "Introduction to Pattern Recognition," Ohm-Sha, Tokyo, Japan, 1998.(in Japanese)

  3. Ueda, N., "Chapter 3: Pattern Recognition Theory," in IEICEJ (Ed.),"Handbook of Electronics, Information and Communication," Asakura-Shoten, Tokyo, Japan, 1998.(in Japanese)

  4. Ueda, N., "Chapter 9: Vector Quantization," in Amari, S. (Ed.),"Handbook of Brain Science," Asakura-Shoten, Tokyo, Japan, 1995.(in Japanese)

  5. NTT Human Interface Laboratory, Project RTV, Japanese translation of "Horn, B. K. P., Robot Vision, MIT-Press, 1986" Asakura-Shoten, Tokyo, Japan, 1993. (in Japanese)


JapanesebHomebOur Group | NTT CS Labs.