研究者詳細 - 田向　権

論文 - 田向　権

分割表示420 件中 201 - 220 件目／全件表示 >>

A memory-based entorhinal-hippocampal model and its FPGA implementation by on-chip RAMs 査読有り

Kawashima I., Tateno K., Morie T., Tamukoh H.

Proceedings - IEEE International Symposium on Circuits and Systems 2022-May 491 - 495 2022年01月

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

Artificial general intelligence, which imitates the human brain, is aspired. Episodic memories are considered to be a key feature in building human brain functions. This paper proposes a memory-based entorhinal-hippocampal model that encodes spatial and non-spatial information, essential to realize episodic memories. The model works as a memory that stores the location of objects and events as neural activity packets. This paper also proposes an area-efficient hardware implementation method for field-programmable gate arrays (FPGAs). Our proposal utilizes on-chip random access memories (RAMs) to achieve a large-scale implementation of our model. Circuit simulations validated the behavior of our hardware-friendly model. The results of logic synthesis revealed the area efficiency of the FPGA implementation method that utilizes on-chip RAMs.

DOI： 10.1109/ISCAS48785.2022.9937768

Scopus

その他リンク： https://www.scopus.com/inward/record.uri?partnerID=HzOxMe3b&scp=85142534523&origin=inward

A dataset generation for object recognition and a tool for generating ROS2 FPGA node 査読有り国際誌

Hayato Amano, Hayato Mori, Akinobu Mizutani, Tomohiro Ono, Yuma Yoshimoto, Takeshi Ohkawa, Hakaru Tamukoh

2021 International Conference on Field-Programmable Technology 2021年12月

An area-efficient multiply-accumulation architecture and implementations for time-domain neural processing 査読有り国際誌

Ichiro Kawashima, Yuichi Katori, Takashi Morie, Hakaru Tamukoh

2021 International Conference on Field-Programmable Technology 2021年12月

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

Yuichiro Tanaka, Hakaru Tamukoh

The 2021 NonLinear Science Workshop 2021年12月

Cycle-Generative Adversarial Network for Generating a Pseudo Realistic Food Dataset Using RGB and Depth Images 査読有り

Obada Al aama, Yuma Yoshimoto and Hakaru Tamukoh

Journal of Advances in Artificial Life Robotics(JAALR) 2 ( 3 ) 345 - 350 2021年12月

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

Akinobu Mizutani, Yuichiro Tanaka, Hakaru Tamukoh, Yuichi Katori, Katsumi Tateno, Takashi Morie

2021 International Symposium on Intelligent Signal Processing and Communication Systems (ISPACS) ( IEEE ) 2021年11月

Open Set Recognition Using the Feature Space of Deep Neural Networks 査読有り国際誌

Daiju Kanaoka, Yuichiro Tanaka, Hakaru Tamukoh

2021 International Symposium on Intelligent Signal Processing and Communication Systems (ISPACS) ( IEEE ) 2021年11月

A Color Image Quantization Method Considering Chromatic Visual Impression 査読有り国際誌

Fukuda Y., Kubota R., Tamukoh H.

Proceedings of ISCIT 2021: 2021 20th International Symposium on Communications and Information Technologies: Quest for Quality of Life and Smart City 24 - 29 2021年10月

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

In recent years, many high-precision color image quantization (CIQ) methods have been proposed. However, they do not consider human visual impression, exposing the image to the possibility of altering its visual impression. In this paper, we propose a novel CIQ method that considers human visual impression. An impression is calculated by using a saliency map of an original image and the frequency of each of its colors to prevents CIQ from changing the impression of the image. Quantitative and qualitative evaluations of the experimental results demonstrate that the proposed method preserves the impressionistic colors better than the general CIQ methods.

DOI： 10.1109/ISCIT52804.2021.9590610

Scopus

その他リンク： https://www.scopus.com/inward/record.uri?partnerID=HzOxMe3b&scp=85119601741&origin=inward

ReLU Functions using Finite State Machines for Stochastic Computing 査読有り国際誌

Kanta Yoshioka, Ichiro Kawashima, Hakaru Tamukoh

International Workshop on Smart Info-Media Systems in Asia RS1-5 40 2021年09月

記述言語：英語掲載種別：研究論文（学術雑誌）

This study presents novel ReLU functions-based on stochastic computing (SC-based ReLU). The conventional SC-based ReLU for an addition method using approximate parallel counter (APC), which outputs the sum of multiple inputs every clock cycle works as a ReLU using accumulator. However, this conventional method loses the high fault tolerance, which is one of the advantages of stochastic computing (SC). Therefore, we propose an SC-based ReLU using a finite state machine (FSM) instead of an accumulator for an addition method using a multiplexer (MUX) which determines the outputs stochastically. For example, if an error occurs in the value of the accumulator in the conventional method, all subsequent operations will be wrong. However, in the case of the proposed SC-based ReLU using FSM, even if an error occurs in the current state of the FSM, it quickly returns the correct state of the FSM. Thus, the proposed SC-based ReLU using FSM for MUX is more fault tolerant than the conventional SC-based ReLU using the accumulator. However, the accuracy of the addition methods using MUX is poor because the output is determined stochastically, and a large length of bitstream (BSL) is required for accurate calculation. As the BSL becomes larger, the latency for the calculation increases, decreasing the performance. Therefore, we propose a SC-based ReLU using FSM for APC. The addition method using APC doesn’t require BSL as large as the addition method using MUX to obtain correct calculation results. Compared with the conventional SC-based ReLU using an accumulator for APC, the proposed SC-based ReLU using FSM for APC shows sufficient accuracy even with a small BSL. The proposed SC-based ReLU using FSM has also a high fault tolerance,

DOI： 10.34385/proc.66.RS1-5

In-materio reservoir computing in a sulfonated polyaniline network 査読有り国際誌

Yuki Usami, Bram van de Ven, Dilu G. Mathew, Hakaru Tamukoh　他

Advanced Materials ( Wiley-VCH ) 33 ( 48 ) 2021年09月

A sub-model detachable convolutional neural network 査読有り

Fuengfusin N., Tamukoh H.

Journal of Robotics, Networking and Artificial Life 8 ( 1 ) 52 - 55 2021年06月

担当区分：最終著者記述言語：英語掲載種別：研究論文（学術雑誌）

In this research, we propose a Convolutional Network with sub-Networks (CNSN), i.e., a Convolutional Neural Network (CNN) or base-model that can be divided into sub-models on demand. The CNN architecture, entails that feature map shapes are varied throughout the model, therefore, the hidden layer within CNN may not directly process an input image without modification. To address this problem, we propose a step-down convolutional layer, which is a convolutional layer acting as an input layer for the sub-model. This step-down convolutional layer reshapes and processes an input image to a preferred representation to the sub-model. To train CNSN, we treat the base-model and sub-models as distinct models. Each model is forward-and back-propagated separately. Using multi-model loss, i.e., a linear combination of losses from base-model and sub-models, we thus update model parameters that can be utilized in both base-model and sub-models.

DOI： 10.2991/jrnal.k.210521.012

Kyutacar

Scopus

その他リンク： https://www.scopus.com/inward/record.uri?partnerID=HzOxMe3b&scp=85120732958&origin=inward

FPGA Implementation of Pulse-Coupled Phase Oscillators working as a Reservoir at the Edge of Chaos 査読有り国際誌

Dinda Pramanta, Hakaru Tamukoh

2021 IEEE International Symposium on Circuits and Systems 2021年05月

Mixed-precision weights network for field-programmable gate array 査読有り

Fuengfusin N., Tamukoh H.

PLoS ONE 16 ( 5 May 2021 ) 2021年05月

担当区分：最終著者記述言語：英語掲載種別：研究論文（学術雑誌）

In this study, we introduced a mixed-precision weights network (MPWN), which is a quantization neural network that jointly utilizes three different weight spaces: binary {−1,1}, ternary {−1,0,1}, and 32-bit floating-point. We further developed the MPWN from both software and hardware aspects. From the software aspect, we evaluated the MPWN on the Fashion-MNIST and CIFAR10 datasets. We systematized the accuracy sparsity bit score, which is a linear combination of accuracy, sparsity, and number of bits. This score allows Bayesian optimization to be used efficiently to search for MPWN weight space combinations. From the hardware aspect, we proposed XOR signed-bits to explore floating-point and binary weight spaces in the MPWN. XOR signed-bits is an efficient implementation equivalent to multiplication of floating-point and binary weight spaces. Using the concept from XOR signed bits, we also provide a ternary bitwise operation that is an efficient implementation equivalent to the multiplication of floating-point and ternary weight space. To demonstrate the compatibility of the MPWN with hardware implementation, we synthesized and implemented the MPWN in a field-programmable gate array using high-level synthesis. Our proposed MPWN implementation utilized up to 1.68-4.89 times less hardware resources depending on the type of resources than a conventional 32-bit floating-point model. In addition, our implementation reduced the latency up to 31.55 times compared to 32-bit floating-point model without optimizations.

DOI： 10.1371/journal.pone.0251329

Scopus

その他リンク： https://www.scopus.com/inward/record.uri?partnerID=HzOxMe3b&scp=85105677409&origin=inward

Object Recognition Using Flexible Tactile Sensor 査読有り国際誌

Shoshi Tokuno, Yuichiro Tanaka, Takumi Kawasetsu, Koh Hosoda, and Hakaru Tamukoh

Proceedings of Asia Pacific Conference on Robot IoT System Development and Platform 2020 81 - 82 2021年03月

Network with sub-networks: Layer-wise detachable neural network 査読有り

Fuengfusin N., Tamukoh H.

Journal of Robotics, Networking and Artificial Life 7 ( 4 ) 240 - 244 2021年03月

担当区分：最終著者記述言語：英語掲載種別：研究論文（学術雑誌）

In this paper, we introduce a network with sub-networks: a neural network whose layers can be detached into sub-neural networks during the inference phase. To develop trainable parameters that can be inserted into both base-model and sub-models, first, the parameters of sub-models are duplicated in the base-model. Each model is separately forward-propagated, and all models are grouped into pairs. Gradients from selected pairs of networks are averaged and used to update both networks. With the Modified National Institute of Standards and Technology (MNIST) and Fashion-MNIST datasets, our base-model achieves identical test-accuracy to that of regularly trained models. However, the sub-models result in lower test-accuracy. Nevertheless, the sub-models serve as alternative approaches with fewer parameters than those of regular models.

DOI： 10.2991/jrnal.k.201215.006

Kyutacar

Scopus

その他リンク： https://www.scopus.com/inward/record.uri?partnerID=HzOxMe3b&scp=85103048798&origin=inward

An efficient hardware-oriented dropout algorithm 査読有り

Yeoh Y.J., Morie T., Tamukoh H.

Neurocomputing 427 191 - 200 2021年02月

担当区分：最終著者記述言語：英語掲載種別：研究論文（学術雑誌）

This paper proposes a hardware-oriented dropout algorithm, which is efficient for field programmable gate array (FPGA) implementation. In deep neural networks (DNNs), overfitting occurs when networks are overtrained and adapt too well to training data. Consequently, they fail in predicting unseen data used as test data. Dropout is a common technique that is often applied in DNNs to overcome this problem. In general, implementing such training algorithms of DNNs in embedded systems is difficult due to power and memory constraints. Training DNNs is power-, time-, and memory- intensive; however, embedded systems require low power consumption and real-time processing. An FPGA is suitable for embedded systems for its parallel processing characteristic and low operating power; however, due to its limited memory and different architecture, it is difficult to apply general neural network algorithms. Therefore, we propose a hardware-oriented dropout algorithm that can effectively utilize the characteristics of an FPGA with less memory required. Software program verification demonstrates that the performance of the proposed method is identical to that of conventional dropout, and hardware synthesis demonstrates that it results in significant resource reduction.

DOI： 10.1016/j.neucom.2020.11.055

Scopus

その他リンク： https://www.scopus.com/inward/record.uri?partnerID=HzOxMe3b&scp=85098454549&origin=inward

Hardware-oriented algorithm of reservoir computing based on chaotic Boltzmann machines 査読有り国際誌

Ichiro Kawashima, Yuichi Katori, Takashi Morie and Hakaru Tamukoh,

the volume of Journal of Physics: Conference Series (JPCS) 2021年02月

Synthesis of realistic food dataset using generative adversarial network based on RGB and depth images 査読有り

Al aama Obada, Tamukoh Hakaru

人工生命とロボットに関する国際会議予稿集 ( 株式会社ALife Robotics ) 26 16 - 19 2021年01月

担当区分：最終著者記述言語：英語掲載種別：研究論文（学術雑誌）

Constructing a large food dataset is time and effort consuming due to the need to cover the feature variations of food items. Hence, a huge data is needed for training neural networks. This paper aims to advocate the Cycle-GAN to build up large food dataset based on large number of simulated images and relatively few real captured images thus obtaining more realistic images effortlessly compared with traditional capturing. Real RGB and depth images of variant food samples allocated over turntable were captured in three different angles using real-sense depth camera with different backgrounds. Furthermore, for simulated images, the Autodesk 3D_Maya software was employed using the same parameters of captured real images. Results showed that generally, realistic style transfer on simulated food objects was obtained as a result of employing Cycle-GAN. GAN proved to be an efficient tool that could minimize imaging efforts resulting in realistic images.

DOI： 10.5954/icarob.2021.os19-4

Kyutacar

CiNii Research

Influence of fpga implementation methods in high-level synthesis 査読有り

Watanabe Y., Tamukoh H.

Proceedings of International Conference on Artificial Life and Robotics 2021 10 - 11 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 explain about how the difference of implementation methods written in C++ in High-Level Synthesis (HLS) influences on latency for tiny You only look once (YOLO) v2, a real-time object detection system to infer on an FPGA. To utilize features of FPGA, we need to implement hardware-oriented algorithms such as the weight binalization. We primarily focus on convolution in tiny YOLO v2 network and we report execution results on the Xilinx SDSoC development environment to know whether methods are appropriate or not.

DOI： 10.5954/ICAROB.2021.OS19-2

Scopus

その他リンク： https://www.scopus.com/inward/record.uri?partnerID=HzOxMe3b&scp=85108833369&origin=inward

Convolutional network with sub-networks 査読有り

Fuengfusin N., Tamukoh H.

Proceedings of International Conference on Artificial Life and Robotics 2021 6 - 9 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 convolutional network with sub-networks (CNSN), a convolutional neural network (CNN) that can be detached into sub-models on fly. Due to a conventional design of CNN, shapes of feature map are varied throughout the model. Therefore, the hidden layer within CNN may not directly process the input image without any modifications. To address this problem, we propose a step-down convolutional layer, a convolutional layer which acts as an input layer for the sub-model. The step-down convolutional layer reshapes the input image to a preferred representation to the sub-model. To train CNSN, we treat the base-model and sub-models as different models. We separately forward-and back-propagate each model. By using multi-model loss, a linear combination of losses from base-and sub-models, we can update weights that can be utilized in both base-and sub-models.

DOI： 10.5954/ICAROB.2021.OS19-1

Scopus

その他リンク： https://www.scopus.com/inward/record.uri?partnerID=HzOxMe3b&scp=85108779535&origin=inward

　前のページ - 次のページ　

<田向 権>

論文 - 田向 権

<田向　権>

論文 - 田向　権