村田 昇

研究成果

年別の研究成果 1994 2004 2010 2011 2012 2013 2014 2015 2016 2018 2019 2023

• 62 Conference contribution
• 55 Article
• 7 Letter
• 5 Conference article
• 7 その他
  • 4 Chapter
  • 2 Paper
  • 1 Review article

年別の研究成果

年別の研究成果

検索結果

• Article

  Fast and robust multiplane single-molecule localization microscopy using a deep neural network

  Aritake, T., Hino, H., Namiki, S., Asanuma, D., Hirose, K. & Murata, N., 2021 9月 3, In: Neurocomputing. 451, p. 279-289 11 p.

  研究成果: Article › 査読

  Open Access

  • Single Molecule Imaging 100%
  • Microscopic examination 78%
  • Molecules 70%
  • Deep neural networks 70%
  • Microscopy 60%

• Fast Multi-Objective Optimization of Magnetic Shield Shape by Combining Auto-Encoder and Level-Set Method

  Oda, K., Kawamata, R., Wakao, S. & Murata, N., 2021 7月, In: IEEE Transactions on Magnetics. 57, 7, 9408617.

  研究成果: Article › 査読

  • Multiobjective optimization 100%
  • Shape 69%
  • Set theory 68%
  4 被引用数 (Scopus)

• Geometrical properties of Nu support vector machines with different norms

  Ikeda, K. & Murata, N., 2005 11月 1, In: Neural Computation. 17, 11, p. 2508-2529 22 p.

  研究成果: Article › 査読

  • Support Vector Machine 100%
  • Linear Programming 27%
  • Programming 15%
  • Computational 14%
  • Experiment 10%
  20 被引用数 (Scopus)

• Geometry of EM and related iterative algorithms

  Hino, H., Akaho, S. & Murata, N., 2022, (Accepted/In press) In: Information Geometry.

  研究成果: Article › 査読

  Open Access

  • Expectation Maximization 100%
  • Iterative Algorithm 70%
  • Expectation-maximization Algorithm 59%
  • Learning 45%
  • Geometry 45%

• Gray-box modeling for prediction and control of molten steel temperature in tundish

  Ahmad, I., Kano, M., Hasebe, S., Kitada, H. & Murata, N., 2014 4月, In: Journal of Process Control. 24, 4, p. 375-382 8 p.

  研究成果: Article › 査読

  • Steel 100%
  • Molten materials 81%
  • Prediction 67%
  • Modeling 54%
  • Temperature 33%
  35 被引用数 (Scopus)

• High-performance prediction of molten steel temperature in tundish through gray-box model

  Okura, T., Ahmad, I., Kano, M., Hasebe, S., Kitada, H. & Murata, N., 2013, In: isij international. 53, 1, p. 76-80 5 p.

  研究成果: Article › 査読

  • Tundish 100%
  • Molten materials 55%
  • Steel 32%
  • Temperature 22%
  • Random forests 15%
  17 被引用数 (Scopus)

• Improving Generalization Performance of Natural Gradient Learning Using Optimized Regularization by NIC

  Park, H., Murata, N. & Amari, S. I., 2004 2月 1, In: Neural Computation. 16, 2, p. 355-382 28 p.

  研究成果: Article › 査読

  • Psychological Generalization 100%
  • Learning 55%
  • Performance 28%
  • Computational 26%
  • Information Services 18%
  13 被引用数 (Scopus)

• Independent component analysis for unaveraged single-trial MEG data decomposition and single-dipole source localization

  Cao, J., Murata, N., Amari, S. I., Cichocki, A. & Takeda, T., 2002 12月, In: Neurocomputing. 49, 1-4, p. 255-277 23 p.

  研究成果: Article › 査読

  • Independent component analysis 100%
  • Phantoms 96%
  • Post and Core Technique 67%
  • Decomposition 65%
  • Source separation 58%
  42 被引用数 (Scopus)

• Information estimators for weighted observations

  Hino, H. & Murata, N., 2013 10月, In: Neural Networks. 46, p. 260-275 16 p.

  研究成果: Article › 査読

  • Entropy 100%
  • Data Compression 67%
  • Statistics 64%
  • Information Theory 62%
  • Weights and Measures 53%
  9 被引用数 (Scopus)

• Information geometry of modal linear regression

  Sando, K., Akaho, S., Murata, N. & Hino, H., 2019 6月 1, In: Information Geometry. 2, 1, p. 43-75 33 p.

  研究成果: Article › 査読

  Open Access

  • Information Geometry 100%
  • Linear regression 75%
  • Expectation-maximization Algorithm 53%
  • Geometry 45%
  • Influence Function 18%
  4 被引用数 (Scopus)

• Information geometry of U-Boost and Bregman divergence

  Murata, N., Takenouchi, T., Kanamori, T. & Eguchi, S., 2004 7月 1, In: Neural Computation. 16, 7, p. 1437-1481 45 p.

  研究成果: Article › 査読

  • Geometry 100%
  • Divergence 75%
  • Pythagorean 34%
  • Classifier 32%
  • Machine Learning 30%
  126 被引用数 (Scopus)

• Learning ancestral atom via sparse coding

  Aritake, T., Hino, H. & Murata, N., 2013, In: IEEE Journal on Selected Topics in Signal Processing. 7, 4, p. 586-594 9 p., 6412707.

  研究成果: Article › 査読

  • Atoms 100%
  • Glossaries 93%
  • Wavelet analysis 12%
  • Experiments 3%
  3 被引用数 (Scopus)

• mmpp: A package for calculating similarity and distance metrics for simple and marked temporal point processes

  Hino, H., Takano, K. & Murata, N., 2015, In: R Journal. 7, 2, p. 237-248 12 p.

  研究成果: Article › 査読

  • Point Process 100%
  • Distance Metric 95%
  • Similarity 60%
  • Metric 35%
  • Marked Point Process 28%
  4 被引用数 (Scopus)

• Multi-frame image super resolution based on sparse coding

  Kato, T., Hino, H. & Murata, N., 2015 6月 1, In: Neural Networks. 66, p. 64-78 15 p.

  研究成果: Article › 査読

  • Image resolution 100%
  • Optical resolving power 49%
  • Pixels 13%
  • Observation 13%
  • Degradation 12%
  30 被引用数 (Scopus)

• Multi-Objective Topology Optimization of Synchronous Reluctance Motor Using Response Surface Approximation Derived by Deep Learning

  Shigematsu, H., Wakao, S., Murata, N., Makino, H., Takeuchi, K. & Matsushita, M., 2023 1月, In: IEEJ Transactions on Electrical and Electronic Engineering. 18, 1, p. 120-128 9 p.

  研究成果: Article › 査読

  • Reluctance motors 100%
  • Shape optimization 90%
  • Synchronous motors 86%
  • Deep learning 76%
  • Torque 41%

• Multiple kernel learning with gaussianity measures

  Hino, H., Reyhani, N. & Murata, N., 2012, In: Neural Computation. 24, 7, p. 1853-1881 29 p.

  研究成果: Article › 査読

  • Kernel 100%
  • Kernel Methods 62%
  • Learning 60%
  • Discriminant Analysis 46%
  • Psychological Power 19%
  5 被引用数 (Scopus)

• Multiplicative nonholonomic/Newton-like algorithm

  Akuzawa, T. & Murata, N., 2001 1月 3, In: Chaos, solitons and fractals. 12, 4, p. 785-793 9 p.

  研究成果: Article › 査読

  • Nonholonomic 100%
  • Coset 83%
  • Cost Function 78%
  • newton 78%
  • Cost functions 72%
  8 被引用数 (Scopus)

• Network Information Criterion—Determining the Number of Hidden Units for an Artificial Neural Network Model

  Murata, N., Yoshizawa, S. & Amari, S. I., 1994 11月, In: IEEE Transactions on Neural Networks. 5, 6, p. 865-872 8 p.

  研究成果: Article › 査読

  • Neural networks 100%
  447 被引用数 (Scopus)

• Neural network with unbounded activation functions is universal approximator

  Sonoda, S. & Murata, N., 2017 9月, In: Applied and Computational Harmonic Analysis. 43, 2, p. 233-268 36 p.

  研究成果: Article › 査読

  Open Access

  • Ridgelets 100%
  • Radon 76%
  • Activation Function 71%
  • Back Propagation 60%
  • Neural Networks 56%
  124 被引用数 (Scopus)

• Neuromagnetic responses to chords are modified by preceding musical scale

  Otsuka, A., Kuriki, S., Murata, N. & Hasegawa, T., 2008 1月, In: Neuroscience Research. 60, 1, p. 50-55 6 p.

  研究成果: Article › 査読

  • Auditory Cortex 100%
  • Psychology 28%
  5 被引用数 (Scopus)

• Non-parametric entropy estimators based on simple linear regression

  Hino, H., Koshijima, K. & Murata, N., 2015 9月, In: Computational Statistics and Data Analysis. 89, p. 72-84 13 p., 6063.

  研究成果: Article › 査読

  • Simple Linear Regression 100%
  • Linear regression 76%
  • Entropy 63%
  • Estimator 45%
  • Probability density function 36%
  8 被引用数 (Scopus)

• On-line learning in changing environments with applications in supervised and unsupervised learning

  Murata, N., Kawanabe, M., Ziehe, A., Müller, K. R. & Amari, S. I., 2002 6月, In: Neural Networks. 15, 4-6, p. 743-760 18 p.

  研究成果: Article › 査読

  • Unsupervised learning 100%
  • Supervised learning 92%
  • Postal services 70%
  • Learning 64%
  • Time series 37%
  45 被引用数 (Scopus)

• Optical detection of neuron connectivity by random access two-photon microscopy

  Shafeghat, N., Heidarinejad, M., Murata, N., Nakamura, H. & Inoue, T., 2016 4月 1, In: Journal of Neuroscience Methods. 263, p. 48-56 9 p.

  研究成果: Article › 査読

  • Photons 100%
  • Microscopy 78%
  • Neurons 58%
  • Calcium 51%
  • Action Potentials 51%
  6 被引用数 (Scopus)

• Prediction of molten steel temperature in steel making process with uncertainty by integrating gray-box model and bootstrap filter

  Ahmad, I., Kano, M., Hasebe, S., Kitada, H. & Murata, N., 2014, In: JOURNAL OF CHEMICAL ENGINEERING OF JAPAN. 47, 11, p. 827-834 8 p.

  研究成果: Article › 査読

  • Molten materials 100%
  • Tundish 90%
  • Casting Process 69%
  • Cope Reaction 66%
  • Uncertainty 64%
  11 被引用数 (Scopus)

• Regions of unusually high flexibility occur frequently in human genomic DNA

  Kimura, H., Kageyama, D., Furuya, M., Sugiyama, S., Murata, N. & Ohyama, T., 2013, In: Bioscience, Biotechnology and Biochemistry. 77, 3, p. 612-617 6 p.

  研究成果: Article › 査読

  • DNA Sequence 100%
  • Flexibility 76%
  • Chromosomes 76%
  • DNA 53%
  • Diptera 52%
  1 被引用数 (Scopus)

• Robust boosting algorithm against mislabeling in multiclass problems

  Takenouchi, T., Eguchi, S., Murata, N. & Kanamori, T., 2008 6月, In: Neural Computation. 20, 6, p. 1596-1630 35 p.

  研究成果: Article › 査読

  • Robustness 100%
  • Divergence 37%
  • Datasets 31%
  • Performance 15%
  18 被引用数 (Scopus)

• Robust loss functions for boosting

  Kanamori, T., Takenouchi, T., Eguchi, S. & Murata, N., 2007 8月, In: Neural Computation. 19, 8, p. 2183-2244 62 p.

  研究成果: Article › 査読

  • Outliers 91%
  • Statistics 65%
  • Descent 40%
  • Experiment 26%
  37 被引用数 (Scopus)

• Sequential extraction of minor components

  Chen, T., Amari, S. I. & Murata, N., 2001 6月, In: Neural Processing Letters. 13, 3, p. 195-201 7 p.

  研究成果: Article › 査読

  • Principal Component Analysis 100%
  • Principal component analysis 88%
  18 被引用数 (Scopus)

• Single-trial magnetoencephalographic data decomposition and localization based on independent component analysis approach

  Cao, J., Murata, N., Amari, S. I., Cichocki, A., Takeda, T., Endo, H. & Harada, N., 2000 1月 1, In: IEICE Transactions on Fundamentals of Electronics, Communications and Computer Sciences. E83-A, 9, p. 1757-1765 9 p.

  研究成果: Article › 査読

  • Magnetoencephalography 100%
  • Independent Component Analysis 90%
  • Independent component analysis 72%
  • Brain 48%
  • Decomposition 47%
  14 被引用数 (Scopus)

• Statistical analysis of learning dynamics

  Murata, N. & Amari, S. I., 1999 4月, In: Signal Processing. 74, 1, p. 3-28 26 p.

  研究成果: Article › 査読

  • Statistical methods 100%
  • Deconvolution 68%
  • Signal processing 47%
  28 被引用数 (Scopus)

• Stochastic simulation of biological reactions, and its applications for studying actin polymerization

  Ichikawa, K., Suzuki, T. & Murata, N., 2010 12月, In: Physical Biology. 7, 4, 046010.

  研究成果: Article › 査読

  • Polymerization 100%
  • Actins 82%
  • Cytoskeleton 24%
  • Computer Simulation 22%
  4 被引用数 (Scopus)

• Support vector machines with different norms: Motivation, formulations and results

  Pedroso, J. P. & Murata, N., 2001, In: Pattern Recognition Letters. 22, 12, p. 1263-1272 10 p.

  研究成果: Article › 査読

  • Mathematical programming 100%
  • Linear programming 79%
  • Program processors 73%
  • Support vector machines 69%
  32 被引用数 (Scopus)

• Time-varying transition probability matrix estimation and its application to brand share analysis

  Chiba, T., Hino, H., Akaho, S. & Murata, N., 2017 1月, In: PloS one. 12, 1, e0169981.

  研究成果: Article › 査読

  • Markov Chains 100%
  • Automobiles 79%
  • Datasets 56%
  • Observation 51%
  6 被引用数 (Scopus)

• Topology optimization in magnetic shield design by using density method in combination with CNN

  Isshiki, R., Kawamata, R., Wakao, S. & Murata, N., 2022, (Accepted/In press) In: COMPEL - The International Journal for Computation and Mathematics in Electrical and Electronic Engineering.

  研究成果: Article › 査読

  • Topology Optimization 100%
  • Shape optimization 75%
  • Neural Networks 67%
  • Convolutional neural networks 65%
  • Design 44%

• Transport analysis of infinitely deep neural network

  Sonoda, S. & Murata, N., 2019 2月 1, In: Journal of Machine Learning Research. 20, p. 1-52 52 p.

  研究成果: Article › 査読

  • Deep neural networks 100%
  • Neural Networks 96%
  • Denoising 94%
  • Integral Representation 27%
  • Neural Network Applications 26%
  12 被引用数 (Scopus)

• Tutorial series on brain-inspired computing part 6: Geometrical structure of boosting algorithm

  Kanamori, T., Takenouchi, T. & Murata, N., 2007 1月 24, In: New Generation Computing. 25, 1, p. 117-141 25 p.

  研究成果: Article › 査読

  • Boosting 100%
  • Brain 81%
  • Series 45%
  • Adaptive boosting 43%
  • Learning systems 37%
  1 被引用数 (Scopus)