User profiles for Makoto Yamada

Makoto Yamada

- Verified email at omu.ac.jp - Cited by 7281

Makoto Yamada

- Verified email at oist.jp - Cited by 5366

Analysis of almost-periodic distributed feedback slab waveguides via a fundamental matrix approach

M Yamada, K Sakuda - Applied optics, 1987 - opg.optica.org
A unified approach to obtain the characteristics of almost-periodic grating slab waveguides
including gain in the waveguide is reported. In this approach the waveguides are divided into …

Change-point detection in time-series data by relative density-ratio estimation

S Liu, M Yamada, N Collier, M Sugiyama - Neural Networks, 2013 - Elsevier
The objective of change-point detection is to discover abrupt property changes lying behind
time-series data. In this paper, we present a novel statistical change-point detection …

Graphlime: Local interpretable model explanations for graph neural networks

Q Huang, M Yamada, Y Tian, D Singh… - IEEE Transactions on …, 2022 - ieeexplore.ieee.org
Recently, graph neural networks (GNN) were shown to be successful in effectively representing
graph structured data because of their good performance and generalization ability. …

Gain characteristics of tellurite-based erbium-doped fiber amplifiers for 1.5-µm broadband amplification

Y Ohishi, A Mori, M Yamada, H Ono, Y Nishida… - Optics letters, 1998 - opg.optica.org
The signal-gain characteristics of tellurite-based erbium-doped fiber amplifiers are clarified
based on spectroscopic properties and signal-gain measurements. The potential of tellurite …

High-dimensional feature selection by feature-wise kernelized lasso

M Yamada, W Jitkrittum, L Sigal, EP Xing… - Neural …, 2014 - ieeexplore.ieee.org
The goal of supervised feature selection is to find a subset of input features that are responsible
for predicting output values. The least absolute shrinkage and selection operator (Lasso) …

Transformer dissection: a unified understanding of transformer's attention via the lens of kernel

YHH Tsai, S Bai, M Yamada, LP Morency… - arXiv preprint arXiv …, 2019 - arxiv.org
Transformer is a powerful architecture that achieves superior performance on various
sequence learning tasks, including neural machine translation, language understanding, and …

[PDF][PDF] Intelligent image-activated cell sorting

…, H Tezuka, C Toyokawa, Y Yalikun, M Yamada… - Cell, 2018 - cell.com
A fundamental challenge of biology is to understand the vast heterogeneity of cells, particularly
how cellular composition, structure, and morphology are linked to cellular physiology. …

[HTML][HTML] Addition of docetaxel to oral fluoropyrimidine improves efficacy in patients with stage III gastric cancer: interim analysis of JACCRO GC-07, a randomized …

…, T Yoshikawa, J Matsuyama, M Yamada… - Journal of Clinical …, 2019 - ncbi.nlm.nih.gov
PURPOSE S-1 is a standard postoperative adjuvant chemotherapy for patients with stage II
or III gastric cancer in Asia. Neoadjuvant or perioperative strategies dominate in Western …

Gain-flattened tellurite-based EDFA with a flat amplification bandwidth of 76 nm

M Yamada, A Mori, K Kobayashi, H Ono… - IEEE Photonics …, 1998 - ieeexplore.ieee.org
We describe a tellurite-based Er/sup 3+/-doped fiber amplifier (EDFA) with a flat amplification
bandwidth of 76 nm and a noise figure of less than 7 dB. Furthermore, a parallel-type …

Random features strengthen graph neural networks

R Sato, M Yamada, H Kashima - Proceedings of the 2021 SIAM international …, 2021 - SIAM
Graph neural networks (GNNs) are powerful machine learning models for various graph
learning tasks. Recently, the limitations of the expressive power of various GNN models have …