※一部利用できない機能があります
1.
論文 |
Hirano, Akihiro ; Nakayama, Kenji
概要:
This paper presents efficient implementa- tion of RLS-based adaptive filters with a large number of taps on nVIDIA GeForce graphics processing unit (GPU) and CUDA software development environment. Modification of the order and the
…
combination of calcu- lations reduces the number of accesses to slow off-chip memory. Assigning tasks into multiple threads also takes memory access order into account. For a 4096-tap case, a GPU program is almost three times faster than a CPU program.
続きを見る
|
|||||
2.
論文 |
Hirano, Akihiro ; Nakayama, Kenji
概要:
This paper presents efficient implementa- tion of RLS-based adaptive filters with a large number of taps on nVIDIA GeForce graphics processing unit (GPU) and CUDA software development environment. Modification of the order and the
…
combination of calcu- lations reduces the number of accesses to slow off-chip memory. Assigning tasks into multiple threads also takes memory access order into account. Multiple shader pro- cessor arrays are used to handle a large matrix. For a 8192-tap case, a GPU program is almost 30-times faster than a CPU program. Real-time processing is possible for an 8kHz-sampling and 512-tap case by us- ing 32 shader processors, which is only 25% of GeForce 8800GTS.
続きを見る
|
|||||
3.
論文 |
Nakayama, Kenji
概要:
金沢大学大学院自然科学研究科情報システム<br />金沢大学工学部<br />A simultaneous frequency- and time-domain approximation method for discrete-time
…
filters is proposed. In the method, transfer function coefficients are divided into two subsets, X//1 and X//2, which are employed for optimizing a time response and a frequency response, respectively. Frequency and time responses are optimized through the iterative Chebyshev approximation method and a method of solving linear equations, respectively. At the rth iteration step, the maximum frequency response error, which appeared at the (r minus 1)th step, is minimized, and X//2**(**r** minus **1**) becomes X//2**(**r**). X//1**(**r**) is obtained from linear equations including X//2**(**r**) as a constant. The frequency response at the rth step is evaluated using the above obtained X//1**(**r**) and X//2**(**r**). This means the optimum time response is always guaranteed in the frequency-response approximation procedure. A design example of a symmetrical impulse response shows the new approach is more efficient than conventional methods from the filter order reduction viewpoint.
続きを見る
|
|||||
4.
論文 |
Hara, Kazuyuki ; Nakayama, Kenji
概要:
金沢大学大学院自然科学研究科知能情報・数理<br />A training data selection method is proposed for multilayer neural networks (MLNNs). This met
…
hod selects a small number of the training data, which guarantee both generalization and fast training of the MLNNs applied to pattern classification. The generalization will be satisfied using the data locate close to the boundary of the pattern classes. However, if these data are only used in the training, convergence is slow. This phenomenon is analyzed in this paper. Therefore, in the proposed method, the MLNN is first trained using some number of the data, which are randomly selected (Step 1). The data, for which the output error is relatively large, are selected. Furthermore, they are paired with the nearest data belong to the different class. The newly selected data are further paired with the nearest data. Finally, pairs of the data, which locate close to the boundary, can be found. Using these pairs of the data, the MLNNs are further trained (Step 2). Since, there are some variations to combine Steps 1 and 2, the proposed method can be applied to both off-line and on-line training. The proposed method can reduce the number of the training data, at the same time, can hasten the training. Usefulness is confirmed through computer simulation.
続きを見る
|
|||||
5.
論文 |
Nakayama, Kenji ; Kato, Takuo ; Katayama, Hiroshi
|
|||||
6.
論文 |
Nakayama, Kenji
概要:
A bandlimited signal extrapolation algorithm is proposed. J. A. Cadzow's algorithm (1979) is modified to eliminate undesired outband spectra. An inverse filter stopband response is relaxed by adding small random numbers. A
…
constrained heuristic optimization is suggested that can use arbitrary signal properties as constraints. Through numerical examples, it is shown how regularization techniques can improve SNR (signal-to-noise-ratio) by 20 dB.
続きを見る
|
|||||
7.
論文 |
Keeni, Kanad ; Shimodaira, Hiroshi ; Nakayama, Kenji
概要:
This paper presents an automatic coding scheme for representing the output layer of a neural network. Compared to local representation where the number of output unit is p, the number of output unit required for the proposed representation is
…
close to log p. The output of seven different printers were used for evaluating the performance of the system. The proposed automatic representation gave the average recognition rate of 98.7% for 71 categories.
続きを見る
|
|||||
8.
論文 |
Wang, Youhua ; Ikeda, Kazushi ; Nakayama, Kenji
|
|||||
9.
論文 |
Nakayama, Kenji ; Katayama, Hiroshi
|
|||||
10.
論文 |
Ikeda, Kazushi ; Suzuki, Akihiro ; Nakayama, Kenji
概要:
The effects of the quantization of the parameters of a learning machine are discussed. The learning coefficient should be as small as possible for a better estimate of parameters. On the other hand, when the parameters are quantized, it
…
should be relatively larger in order to avoid the paralysis of learning originated from the quantization. How to choose the learning coefficient is given in this paper from the statistical point of view.
続きを見る
|