研究者詳細 - 田中　悠一朗

論文 - 田中　悠一朗

分割表示55 件中 21 - 40 件目／全件表示 >>

Ensemble Learning of Multiple Readouts for Reservoir Computing 査読有り国際誌

Tanaka Yuichiro, Tamukoh Hakaru

IEICE Proceeding Series ( The Institute of Electronics, Information and Communication Engineers ) 76 509 - 512 2023年09月

担当区分：筆頭著者,　責任著者記述言語：英語掲載種別：研究論文（学術雑誌）

This study proposes a reservoir computing model with multiple readouts and an associated training method to enhance the training capability of reservoir computing. This study conducts a speaker classification task and a word classification task using an audio dataset consisting of digits pronounced by six persons. The experimental results reveal that the proposed model with multiple readouts outperforms a conventional model with a single readout.

DOI： 10.34385/proc.76.c3l-11

Kyutacar

CiNii Research

その他リンク： https://kyutech.repo.nii.ac.jp/records/2000241

Robust Trash Can Lid Opening System 査読有り国際誌

Kosei Isomoto, Yuga Yano, Yuichiro Tanaka, Hakaru Tamukoh

2023 International Workshop on Smart Info-Media Systems in Asia (SISA 2023) 30 - 33 2023年08月

FPGA Implementation of a Chaotic Boltzmann Machine Annealer 査読有り国際誌

Yoshioka K., Katori Y., Tanaka Y., Nomura O., Morie T., Tamukoh H.

Proceedings of the International Joint Conference on Neural Networks 2023-June 2023年06月

記述言語：英語掲載種別：研究論文（国際会議プロシーディングス）

Ising machines are attracting attention for their ability to solve large-scale combinatorial optimization problems because these problems are difficult to solve. To accelerate the computing of Ising machines, implementation of Ising machines with digital circuits such as simulated annealing (SA) machines is in progress. However, these Ising machines on digital circuits require random number generators, which are implemented with large circuit resources. This work focuses on chaotic Boltzmann machines (CBMs), which imitate the stochastic behavior of Boltzmann machines (BMs) with deterministic chaotic dynamics. CBMs are one of the models that work as chaotic simulated annealing (CSA) machines within Ising machines. Therefore, we can implement the Ising machines without random number generators by using CBMs. In conventional work, CSA machines using CBMs (CBM-CSAs) are implemented with some hardware-oriented algorithms, but the CBM-CSA circuit is not optimized for these hardware-oriented algorithms. In the conventional CBM-CSA circuit, memory circuits are implemented separately, which prevents making the CBM-CSA from larger, and neuron circuits require the reset of accumulated values, which causes the increase in the calculation time. To solve these problems, we implement only one large memory circuit to make the CBM-CSA larger and improve the neuron circuits to allow dynamic changes of inputs to arithmetic circuits to inhibit the increase in the calculation time. As a result, we implement a CBM-CSA with 4096 nodes on an FPGA (Alveo U250), and the CBM-CSA can control 16-bit width weights and run at 100MHz. We evaluate the implemented CBM-CSA by solving K4000, max-cut problem, which is one of the combinatorial optimization problems. The best solution of CBM-CSA is comparable to that of the SA on the central processing unit (CPU). Moreover, the CBM-CSA is approximately 600 times as fast as the SA on the CPU and approximately twice as fast as the conventional Ising machine on an FPGA based on the improvements in this work. Furthermore, this work implements one of the highest-performance Ising machines on a single FPGA.

DOI： 10.1109/IJCNN54540.2023.10191342

Kyutacar

Scopus

その他リンク： https://www.scopus.com/inward/record.uri?partnerID=HzOxMe3b&scp=85169581320&origin=inward

Efficient Repetition Coding for Deep Learning Towards Implementation Using Emerging Non-Volatile Memory with Write-Errors 査読有り国際誌

Fuengfusin N., Tamukoh H., Tanaka Y., Nomura O., Morie T.

Proceedings of the International Joint Conference on Neural Networks 2023-June 2023年06月

記述言語：英語掲載種別：研究論文（国際会議プロシーディングス）

Emerging non-volatile memory devices, such as resistive random access memory (ReRAM) and voltage-controlled magnetoresistive random access memory (VC-MRAM), promise low energy consumption for artificial intelligence applications. However, when implementing deep neural networks (DNNs) using such memory devices, write-error may cause millions of bit-flipping to DNN. This easily degrades the DNN performance. To address this problem, we propose a novel repetition coding for deep-learning (RC-DL), which is a repetition coding designed to protect IEEE 32-bit floating-point (FP32) DNN models. Compared to conventional repetition coding, the proposed RC-DL exploits FP32 non-uniform magnitude encoding by increasing the repeat rates to protect sensitive bit positions and reduce the repeat rates to insensitive bit positions. Hence, RC-DL uses a number of bits equivalent to a 3-bit repetition code while delivering the performance close to 11-bit repetition code. We perform extensive Monte Carlo simulations to simulate the write-error property with ImageNet 2012 pretrained models. The DNN models with RC-DL are shown to be operable in the extremely imperfect environment while delivering with only minor reductions in DNN performance.

DOI： 10.1109/IJCNN54540.2023.10191433

Kyutacar

Scopus

その他リンク： https://www.scopus.com/inward/record.uri?partnerID=HzOxMe3b&scp=85169554268&origin=inward

In-material reservoir implementation of reservoir-based convolution 査読有り国際誌

Tanaka Y., Usami Y., Tanaka H., Tamukoh H.

Proceedings - IEEE International Symposium on Circuits and Systems 2023-May 2023年05月

担当区分：筆頭著者,　責任著者記述言語：英語掲載種別：研究論文（国際会議プロシーディングス）

This study aims to implement a reservoir-based convolutional neural network (CNN) on physical reservoir computing (RC) to develop an efficient image recognition system for edge AI. Therefore, we propose a novel reservoir-based convolution circuit system that uses in-material reservoir computing, a type of physical RC made from a sulfonated polyaniline network. The experimental results demonstrate that the proposed circuit system extracts image features in the same way as the original CNN and that a reservoir-based CNN on the in-material RC achieves an accuracy rate of 81.7% in an image classification task while an echo state network-based CNN achieves 87.7%.

DOI： 10.1109/ISCAS46773.2023.10181436

Scopus

その他リンク： https://www.scopus.com/inward/record.uri?partnerID=HzOxMe3b&scp=85167720431&origin=inward

Memory-Efficient Implementation of GMM-MRCoHOG for HumaRecognition Hardware 査読有り

Takemoto R., Nagamine Y., Yoshihiro K., Shibata M., Yamada H., Tanaka Y., Enokida S., Tamukoh H.

Proceedings of the International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications 4 648 - 655 2023年02月

記述言語：英語掲載種別：研究論文（国際会議プロシーディングス）

High-speed and accurate human recognition is necessary to realize safe autonomous mobile robots. Recently, human recognition methods based on deep learning have been studied extensively. However, these methods consume large amounts of power. Therefore, this study focuses on the Gaussian mixture model of multiresolution co-occurrence histograms of oriented gradients (GMM-MRCoHOG), which is a feature extraction method for human recognition that entails lower computational costs compared to deep learning-based methods, and aims to implement its hardware for high-speed, high-accuracy, and low-power human recognition. A digital hardware implementation method of GMM-MRCoHOG has been proposed. However, the method requires numerous look-up tables (LUTs) to store state spaces of GMM-MRCoHOG, thereby impeding the realization of human recognition systems. This study proposes a LUT reduction method to overcome this drawback by standardizing basis function arrangements of Gaussian mixture distributions in GMM-MRCoHOG. Experimental results show that the proposed method is as accurate as the previous method, and the memory required for state spaces consuming LUTs can be reduced to 1/504th of that required in the previous method.

DOI： 10.5220/0011698400003417

Scopus

その他リンク： https://www.scopus.com/inward/record.uri?partnerID=HzOxMe3b&scp=85183596965&origin=inward

Random network device fabricated using Ag2Se nanowires for data augmentation with binarized convolutional neural network 査読有り国際誌

Takumi Kotooka, Yuichiro Tanaka, Hakaru Tamukoh, Yuki Usami, Hirofumi Tanaka

Applied Physics Express 16 ( 1 ) 2023年01月

記述言語：英語掲載種別：研究論文（学術雑誌）

An Ag2Se nanowire random network was fabricated for application as a data augmentation device and combined with a binary convolutional neural network (BCNN) to achieve high accuracy in voice classification tasks. Due to the nonlinear high-dimensional characteristics resulting from the formation of the conductive filament at the cross junction, the Ag2Se device could transform input data into higher-order multiple signals, thereby enhancing the accuracy of the classification task by augmenting input signals. The results indicate that materials can realize data augmentation with the same performance as software, suggesting that material-based hardware can be used as an elemental technology for information processing.

DOI： 10.35848/1882-0786/acae6a

Scopus

その他リンク： https://www.scopus.com/inward/record.uri?partnerID=HzOxMe3b&scp=85146494177&origin=inward

Material computing based on electrochemical dynamics 査読有り

Yuki Usami, Yuichiro Tanaka, Takumi Kotooka, Hakaru Tamukoh, Hirofumi Tanaka

The 4th International Symposium on Neuromorphic AI Hardware 6 - 6 2022年12月

Robust Trash Can Lid Opening System 査読有り

Kosei Isomoto, Yuga Yano, Yuichiro Tanaka, Hakaru Tamukoh

The 4th International Symposium on Neuromorphic AI Hardware 46 - 46 2022年12月

Hardware-oriented Brain-inspired Model with Memory Accumulation and Recall Functions to Generate Actions of Home Service Robots 査読有り

Akinobu Mizutani, Ichiro Kawashima, Yuichiro Tanaka, Hakaru Tamukoh, Katsumi Tateno, Osamu Nomura, Takashi Morie

The 4th International Symposium on Neuromorphic AI Hardware 44 - 44 2022年12月

Resorvoir-based neuron model to emulate cellular neural activity responding to odor in C. elegans 査読有り

Ryosuke Ishibashi, Takumi Nakamura, Noriko Sato, Takeshi Ishihara, Yuichiro Tanaka, Hakaru Tamukoh, Terumasa Tokunaga

The 4th International Symposium on Neuromorphic AI Hardware 42 - 42 2022年12月

Deep Learning Method on Word Level American Sign Language Recognition from Video 査読有り

Arie Rachmad Syulistyo, Yuichiro Tanaka, Hakaru Tamukoh

The 4th International Symposium on Neuromorphic AI Hardware 28 - 28 2022年12月

Reservoir-based 1D convolution 査読有り

Yuichiro Tanaka, Hakaru Tamukoh,

The 4th International Symposium on Neuromorphic AI Hardware 12 - 12 2022年12月

Reservoir computing in the matter based on electrochemical dynamics 査読有り国際誌

Usami Y, Tanaka Y, Tamukoh H, Matsumoto T, van der Wiel W, Tanaka H

16th International Conference on Nanostructured Materials (NANO2022) 2022年06月

Reservoir-based convolution 査読有り国際誌

Yuichiro Tanaka, Hakaru Tamukoh

Nonlinear Theory and Its Applications, IEICE ( IEICE ) 13 ( 2 ) 397 - 402 2022年04月

担当区分：筆頭著者,　責任著者記述言語：英語掲載種別：研究論文（学術雑誌）

<p>Reservoir computing (RC) has attracted attention and has been used in many applications because of its low training cost. Multiple studies using RC for image recognition have been proposed, and some have achieved accuracy rates of greater than 99% on the MNIST dataset. For the Fashion-MNIST and CIFAR-10 datasets, however, they have not yet achieved high accuracy. This study proposes a novel convolutional neural network based on RC that can be optimized by ridge regression rather than back-propagation. The reservoir-based network has multiple reservoirs with various leak rates to extract features with various spatial frequencies from the inputs. The experimental results show that the performance of the proposed model achieves higher accuracy rates in the mentioned datasets compared with those of other reservoir-based image recognition approaches.</p>

DOI： 10.1587/nolta.13.397

Kyutacar

CiNii Research

その他リンク： http://hdl.handle.net/10228/00009117

Hardware-oriented Algorithm for Human Detection using GMM-MRCoHOG Features 査読有り国際誌

Takemoto R., Nagamine Y., Yoshihiro K., Shibata M., Yamada H., Tanaka Y., Enokida S., Tamukoh H.

Proceedings of the International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications 4 749 - 757 2022年02月

記述言語：英語掲載種別：研究論文（国際会議プロシーディングス）

In this research, we focus on Gaussian mixture model-multiresolution co-occurrence histograms of oriented gradients (GMM-MRCoHOG) features using luminance gradients in images and propose a hardware-oriented algorithm of GMM-MRCoHOG to implement it on a field programmable gate array (FPGA). The proposed method simplifies the calculation of luminance gradients, which is a high-cost operation in the conventional algorithm, by using lookup tables to reduce the circuit size. We also designed a human-detection digital architecture of the proposed algorithm for FPGA implementation using high-level synthesis. The verification results showed that the processing speed of the proposed architecture was approximately 123 times faster than that of the FPGA implementation of VGG-16.

DOI： 10.5220/0010848100003124

Kyutacar

Scopus

その他リンク： https://www.scopus.com/inward/record.uri?partnerID=HzOxMe3b&scp=85182929508&origin=inward

Applying Center Loss to Multidimensional Feature Space in Deep Neural Networks for Open-set Recognition 査読有り国際誌

Daiju Kanaoka, Yuichiro Tanaka, Hakaru Tamukoh

17th International Conference on Computer Vision Theory and Applications (VISAPP2022) 5 359 - 365 2022年02月

Applying Center Loss to Multidimensional Feature Space in Deep Neural Networks for Open-set Recognition 査読有り

Kanaoka D., Tanaka Y., Tamukoh H.

Proceedings of the International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications 5 359 - 365 2022年01月

記述言語：英語掲載種別：研究論文（国際会議プロシーディングス）

With the advent of deep learning, significant improvements in image recognition performance have been achieved. In image recognition, it is generally assumed that all the test data are composed of known classes. This approach is termed as closed-set recognition. In closed-set recognition, when an untrained, unknown class is input, it is recognized as one of the trained classes. The method whereby an unknown image is recognized as unknown when it is input is termed as open-set recognition. Although several open-set recognition methods have been proposed, none of these previous methods excel in terms of all three evaluation items: learning cost, recognition performance, and scalability from closed-set recognition models. To address this, we propose an open-set recognition method using the distance between features in the multidimensional feature space of neural networks. By applying center loss to the feature space, we aim to maintain the classification accuracy of closed-set recognition and improve the unknown detection performance. In our experiments, we achieved state-of-the-art performance on the MNIST, SVHN, and CIFAR-10 datasets. In addition, the proposed approach shows excellent performance in terms of the three evaluation items.

DOI： 10.5220/0010816600003124

Scopus

その他リンク： https://www.scopus.com/inward/record.uri?partnerID=HzOxMe3b&scp=85143999490&origin=inward

Reservoir-based Convolutional Neural Network 査読有り国際誌

Yuichiro Tanaka, Hakaru Tamukoh

The 2021 NonLinear Science Workshop NLSW-34 2021年12月

Brain-inspired neural network navigation system with hippocampus, prefrontal cortex, and amygdala functions 査読有り

Mizutani A., Tanaka Y., Tamukoh H., Katori Y., Tateno K., Morie T.

ISPACS 2021 - International Symposium on Intelligent Signal Processing and Communication Systems: 5G Dream to Reality, Proceeding 2021年01月

記述言語：英語掲載種別：研究論文（国際会議プロシーディングス）

We propose a brain-inspired neural network model consisting of the hippocampus, prefrontal cortex, and amygdala models for a navigation system that acquires specific knowledge in home environments from few experiences. The proposed model was evaluated in a home environment using a robot simulator. In the experiment, the robot determines a path for navigation based on the knowledge acquired by the brain-inspired model.

DOI： 10.1109/ISPACS51563.2021.9651058

Kyutacar

Scopus

その他リンク： https://www.scopus.com/inward/record.uri?partnerID=HzOxMe3b&scp=85124147021&origin=inward

　前のページ - 次のページ　

<田中 悠一朗>

論文 - 田中 悠一朗

<田中　悠一朗>

論文 - 田中　悠一朗