Výsledky vyhledávání - "Ryousei Takano"

Akademický článek

Automated Quantization and Retraining for Neural Network Models Without Labeled Data

Autor: Kundjanasith Thonglek, Keichi Takahashi, Kohei Ichikawa, Chawanat Nakasan, Hidemoto Nakada, Ryousei Takano, Pattara Leelaprute, Hajimu Iida

Publikováno v: IEEE Access, Vol 10, Pp 73818-73834 (2022)

Deploying neural network models to edge devices is becoming increasingly popular because such deployment decreases the response time and ensures better data privacy of services. However, running large models on edge devices poses challenges because o

Externí odkaz: https://doaj.org/article/ad28e64c1db340ec8198e2335e7f0326

Zobrazit plný text záznamu

A Software-based NVM Emulator Supporting Read/Write Asymmetric Latencies

Autor: Takahiro Hirofuchi, Ryousei Takano, Atsushi Koshiba, Mitaro Namiki

Publikováno v: IEICE Transactions on Information and Systems. :2377-2388

Non-volatile memory (NVM) is a promising technology for low-energy and high-capacity main memory of computers. The characteristics of NVM devices, however, tend to be fundamentally different from those of DRAM (i.e., the memory device currently used

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::89e260d45951feade738c888080fbcf8
https://doi.org/10.1587/transinf.2019pap0018

Zobrazit plný text záznamu

kEDM: A Performance-portable Implementation of Empirical Dynamic Modeling using Kokkos

Autor: Kohei Ichikawa, Gerald M. Pao, Jason H. Haga, Ryousei Takano, Keichi Takahashi, George Sugihara, Joseph Park, Wassapon Watanakeesuntorn

Publikováno v: PEARC

Empirical Dynamic Modeling (EDM) is a state-of-the-art non-linear time-series analysis framework. Despite its wide applicability, EDM was not scalable to large datasets due to its expensive computational cost. To overcome this obstacle, researchers h

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::761ef2f28d00e6f601043767b38b85a6
http://arxiv.org/abs/2105.12301

Zobrazit plný text záznamu

Massively Parallel Causal Inference of Whole Brain Dynamics at Single Neuron Resolution

Autor: Keichi Takahashi, Kohei Ichikawa, Gerald M. Pao, Joseph Park, Wassapon Watanakeesuntorn, Jason H. Haga, Ryousei Takano, George Sugihara

Publikováno v: ICPADS

Empirical Dynamic Modeling (EDM) is a nonlinear time series causal inference framework. The latest implementation of EDM, cppEDM, has only been used for small datasets due to computational cost. With the growth of data collection capabilities, there

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::1a5b03c4bb2d64af08e93c06388952a7
https://doi.org/10.1109/icpads51040.2020.00035

Zobrazit plný text záznamu

Scaling Distributed Deep Learning Workloads beyond the Memory Capacity with KARMA

Autor: Aleksandr Drozd, Jens Domke, Truong Thao Nguyen, Lingqi Zhang, Ryousei Takano, Haoyu Zhang, Mohamed Wahib, Satoshi Matsuoka

Publikováno v: SC

The dedicated memory of hardware accelerators can be insufficient to store all weights and/or intermediate states of large deep learning models. Although model parallelism is a viable approach to reduce the memory pressure issue, significant modifica

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::e75e30fc72e6ee4623572db16d2a197c
http://arxiv.org/abs/2008.11421

Zobrazit plný text záznamu

Vyhledávací nástroje:

Upřesnit hledání