H. Ogawa

发表

Projection filter, Wiener filter, and Karhunen-Loève subspaces in digital image restoration

E. Oja, H. Ogawa, 1986 .

Subspace Information Criterion for Model Selection

Masashi Sugiyama, Hidemitsu Ogawa, H. Ogawa, 2001, Neural Computation.

How to design a regularization term for improving generalization

H. Ogawa, A. Nakashima, 1999, ICONIP'99. ANZIIS'99 & ANNES'99 & ACNN'99. 6th International Conference on Neural Information Processing. Proceedings (Cat. No.99EX378).

Neural network learning, generalization and over-learning

Hidemitsu Ogawa, H. Ogawa, 1992 .

Projection filters for image and signal restoration

E. Oja, H. Ogawa, J. Lampinen, 1989, IEEE 1989 International Conference on Systems Engineering.

Pseudo-Duals of Frames with Applications

H. Ogawa, Shidong Li, 2001 .

RKHS-based functional analysis for exact incremental learning

Hidemitsu Ogawa, Sethu Vijayakumar, S. Vijayakumar, 1999, Neurocomputing.

A functional analytic approach to incremental learning in optimally generalizing neural networks

Sethu Vijayakumar, Hidemitsu Ogawa, S. Vijayakumar, 1995, Proceedings of ICNN'95 - International Conference on Neural Networks.

A generalized sampling theorem

H. Ogawa, 1989 .

Improving Generalization Ability through Active Learning

Sethu Vijayakumar, Hidemitsu Ogawa, S. Vijayakumar, 1999 .

Incremental Learning in Optimally Generalizing Neural Networks

Sethu Vijayakumar, Hidemitsu Ogawa, S. Vijayakumar, 1996 .

Training Data Selection for Optimal Generalization with Noise Variance Reduction in

Masashi Sugiyama, Sethu Vijayakumar, Hidemitsu Ogawa, 1998 .

Active Learning for Optimal Generalization in Trigonometric Polynomial Models

H. Ogawa, Masashi Sugiyama, 2001 .

Training the Gradient Field of a Dynamic Hopfield (Recurrent) Network for Classification

H. Ogawa, Craig Hicks, 1992 .

Simultaneous Optimization of Sample Points and Models

H. Ogawa, Masashi Sugiyama, 2007 .

:ge,hf2=$n$?$a$ng=f03x=, Active Learning for Optimal Generalization

H. Ogawa, Masashi Sugiyama, 2007 .

Bias Estimation and Model Selection

H. Ogawa, Masashi Sugiyama, 2007 .

Perturbation Analysis of a Generalization Error Estimator

H. Ogawa, Masashi Sugiyama, Yuta Okabe, 2004 .

On the influence of input noise on a generalization error estimator

H. Ogawa, Masashi Sugiyama, Yuta Okabe, 2004 .

Incremental Active Learning in Consideration of Bias

H. Ogawa, Masashi Sugiyama, 1999 .

Pseudo Orthogonal Bases Give the Optimal Solution to Active Learning in Neural Networks

H. Ogawa, Masashi Sugiyama, 1999 .

Pseudoframes for Subspaces with Applications

H. Ogawa, Shidong Li, 2004 .

Pattern recognition in the presence of noise

Yukihiko Yamashita, Hidemitsu Ogawa, D. Liu, 1995, Pattern Recognit..

What can memorization learning do from noisy training examples?

H. Ogawa, A. Hirabayashi, 1999, ICONIP'99. ANZIIS'99 & ANNES'99 & ACNN'99. 6th International Conference on Neural Information Processing. Proceedings (Cat. No.99EX378).

Optimally generalizing neural networks

Hidemitsu Ogawa, E. Oja, E. Oja, 1991, [Proceedings] 1991 IEEE International Joint Conference on Neural Networks.

Restoration of Printed Images Based on Degradation Models Masashi Sugiyama

H. Ogawa, K. Kambe, Kyosuke Kambe, 2004 .

Image Restoration with Subspace Information Criterion Optimizing Parameters of Linear Filters

H. Ogawa, M. Imaizumi, 2001 .

Subspace Information Criterion Determining Parameters in Linear Filters for Optimal Restoration

H. Ogawa, Masashi Sugiyama, 2001 .

Sampling theorem for surface profiling by white-light interferometry

Hidemitsu Ogawa, H. Ogawa, 小川英光, 2001 .

Release from active learning/model selection dilemma: optimizing sample points and models at the same time

H. Ogawa, Masashi Sugiyama, 2002, Proceedings of the 2002 International Joint Conference on Neural Networks. IJCNN'02 (Cat. No.02CH37290).

Model Selection with Small Samples

Masashi Sugiyama, Hidemitsu Ogawa, H. Ogawa, 2001 .

Neural Nets WIRN Vietri-98

Masashi Sugiyama, Hidemitsu Ogawa, Sethu Vijayakumar, 1998 .

Homogeneous Neural Networks for Principal Component Analysis

Erkki Oja, Hidemitsu Ogawa, Jaroonsakdi Wangviwattana, 1991 .

Can we solve the continuous Karhunen-Loève eigenproblem from discrete data?

Erkki Oja, H. Ogawa, E. Oja, 1986 .

Principal component analysis by homogeneous neural networks, part II: Analysis and extentions of the learning algorithm

Erkki Oja, Hidemitsu Ogawa, Hidemitsu Ogawa, 1992 .

Radon transform and analog coding

Itsuo Kumazawa, Hidemitsu Ogawa, H. Ogawa, 1991 .

Image reconstruction from erroneous projections—radon transform as an analog coding

H. Ogawa, I. Kumazawa, Hiroshi Tajima, 1990 .

Single-shot Interferometry of Film-covered Objects

H. Ogawa, K. Kitagawa, Takuto Naito, 2009 .

Error Analysis of Local Model Fitting Method in Single-shot Surface Profiling Tokyo Institute of Technology

H. Ogawa, Masashi Sugiyama, Tatsuya Yokota, 2009 .

The current research of image processing in Tokyo Institute of Technology : Ogawa Lab., Sakai・Yoshida Lab. and Nakajima・Kamei Lab.

Masayuki Nakajima, Yoshinori Sakai, Hidemitsu Ogawa, 1994 .

Theoretical and Experimental Evaluation of the Subspace Information Criterion

Masashi Sugiyama, Hidemitsu Ogawa, H. Ogawa, 2002, Machine Learning.

Active Learning with Model Selection — Simultaneous Optimization of Sample Points and Models for Trigonometric Polynomial Models

Masashi Sugiyama, Hidemitsu Ogawa, H. Ogawa, 2003 .

Optimal design of regularization term and regularization parameter by subspace information criterion

Masashi Sugiyama, Hidemitsu Ogawa, H. Ogawa, 2002, Neural Networks.

Error correcting memorization learning for noisy training examples

Hidemitsu Ogawa, Akira Hirabayashi, Akiko Nakashima, 2001, Neural Networks.

Incremental Active Learning for Optimal Generalization

Masashi Sugiyama, Hidemitsu Ogawa, H. Ogawa, 2000, Neural Computation.

Incremental active learning with bias reduction

Masashi Sugiyama, Hidemitsu Ogawa, H. Ogawa, 2000, Proceedings of the IEEE-INNS-ENNS International Joint Conference on Neural Networks. IJCNN 2000. Neural Computing: New Challenges and Perspectives for the New Millennium.

Active learning with model selection for optimal generalization

Hidemitsu Ogawa, 小川英光, H. Ogawa, 2000 .

Training Data Selection for Optimal Generalization in Trigonometric Polynomial Networks

Masashi Sugiyama, Hidemitsu Ogawa, H. Ogawa, 1999, NIPS.

Pseudo orthogonal bases give the optimal generalization capability in neural network learning

Masashi Sugiyama, Hidemitsu Ogawa, H. Ogawa, 1999, Optics & Photonics.

Incremental projection learning for optimal generalization

Masashi Sugiyama, Hidemitsu Ogawa, H. Ogawa, 2001, Neural Networks.

Modulated Hebb-Oja learning Rule-a method for principal subspace analysis

Hidemitsu Ogawa, Marko Jankovic, H. Ogawa, 2006, IEEE Transactions on Neural Networks.

Time-oriented hierarchical method for computation of principal components using subspace learning algorithm

MARKO JANKOVIC, HIDEMITSU OGAWA, H. Ogawa, 2004, Int. J. Neural Syst..