Search Results for author: Takumi Honda

Found 3 papers, 1 papers with code

Direct Quantized Training of Language Models with Stochastic Rounding

1 code implementation6 Dec 2024 Kaiyan Zhao, Tsuguchika Tabaru, Kenichi Kobayashi, Takumi Honda, Masafumi Yamazaki, Yoshimasa Tsuruoka

Although recent quantized Large Language Models (LLMs), such as BitNet, have paved the way for significant reduction in memory usage during deployment with binary or ternary weights, training these models still demands substantial memory footprints.

Yet Another Accelerated SGD: ResNet-50 Training on ImageNet in 74.7 seconds

no code implementations29 Mar 2019 Masafumi Yamazaki, Akihiko Kasagi, Akihiro Tabuchi, Takumi Honda, Masahiro Miwa, Naoto Fukumoto, Tsuguchika Tabaru, Atsushi Ike, Kohta Nakashima

There has been a strong demand for algorithms that can execute machine learning as faster as possible and the speed of deep learning has accelerated by 30 times only in the past two years.

Deep Learning

Cannot find the paper you are looking for? You can Submit a new open access paper.