Department of Computer and Mathematical Sciences, Graduate School of Information Sciences, Tohoku University (2003年 CiNii収録論文より)

Search authors sharing the same name

Articles:  1-7 of 7

  • Vector Quantization Codebook Design Using the Law-of-the Jungle Algorithm

    TAKIZAWA Hiroyuki , NAKAJIMA Taira , SANO Kentaro , KOBAYASHI Hiroaki , NAKAMURA Tadao

    The equidistortion principle [1] has recently been proposed as a basic principle for design of an optimal vector quantization (VQ) codebook. The equidistortion principle adjusts all codebook vectors s …

    IEICE Transactions on Information and Systems 86(6), 1068-1077, 2003-06-01

    References (20) Cited by (2)

  • A Pre-attributed Resampling Algorithm for Controlled-Precision Volume Ray-Casting


    Accurate volume rendering is essential for some visualization applications, e.g., medical imaging. However, the computationally expensive feature of conventional volume rendering algorithms for high-q …

    情報処理学会論文誌. ハイパフォーマンスコンピューティングシステム 41(1), 113-124, 2000-08-15

    References (19)

  • An Active Learning Algorithm Based on Existing Training Data

    TAKIZAWA Hiroyuki , NAKAJIMA Taira , KOBAYASHI Hiroaki , NAKAMURA Tadao

    A multilayer perceptron is usually considered a passive learner that only receives given training data. However, if a multilayer perceptron actively gathers training data that resolve its uncertainty …

    IEICE transactions on information and systems 83(1), 90-99, 2000-01-25

    References (20)

  • Data-Parallel Volume Rendering with Adaptive Volume Subdivision

    SANO Kentaro , KITAJIMA Hiroyuki , KOBAYASHI Hiroaki , NAKAMURA Tadao

    A data-parallel processing approach is promising for real-time volume rendering because of the massive parallelism in volume rendering. In data-parallel volume rendering, local results processing elem …

    IEICE transactions on information and systems 83(1), 80-89, 2000-01-25

    References (16)

  • A Topology Preserving Neural Network for Nonstationary Distributions

    NAKAJIMA Taira , TAKIZAWA Hiroyuki , KOBAYSHI Hiroaki , NAKAMURA Tadao

    We propose a learning algorithm for self-organizing neural networks to form a topology preserving map from an input manifold whose topology may dynamically change. Experimental results show that the n …

    IEICE Trans. Inf. & Syst. 82(7), 1131-1135, 1999-07-25

    References (8) Cited by (2)

  • Acceleration Techniques for the Network Inversion Algorithm

    TAKIZAWA Hiroyuki , NAKAJIMA Taira , NISHI Masaaki , KOBAYASHI Hiroaki , NAKAMURA Tadao

    We apply two acceleration techniques for the backpropagation algorithm to an iterative gradient descent algorithm called the network inversion algorithm. Experimental results show that these technique …

    IEICE Trans. Inf. & Syst. 82(2), 508-511, 1999-02-25

    References (10) Cited by (1)

  • Kohonen Learning with a Mechanism, the Law of the Jungle, Capable of Dealing with Nonstationary Probability Distribution Functions

    NAKAJIMA Taira , TAKIZAWA Hiroyuki , KOBAYASHI Hiroaki , NAKAMURA Tadao

    We present a mechanism, named the law of the jungle(LOJ), to improve the Kohonen learning. The LOJ is used to be an adaptive vector quantizer for approximating nonstationary probability distribution f …

    IEICE Transactions on Information and Systems 81(6), 584-591, 1998-06-25

    References (12) Cited by (3)

Page Top