activity
20182023
most citedAddressing Gap between Training Data and Deployed Environment by On-Device Learning

13 citations · 14 across the 6 of their papers we have counts for

collaborators
Showing cs.LGShow all

8 papers · 1 filter

cs.LG2023

A Sequential Concept Drift Detection Method for On-Device Learning on Low-End Edge Devices

Takeya Yamada, Hiroki Matsutani

A practical issue of edge AI systems is that data distributions of trained dataset and deployed environment may differ due to noise and environmental changes over time. Such a phen…

cs.LG2022

Federated Learning of Neural ODE Models with Different Iteration Counts

Yuto Hoshino, Hiroki Kawakami, Hiroki Matsutani

Federated learning is a distributed machine learning approach in which clients train models locally with their own data and upload them to a server so that their trained results ar…

cs.LG2022★ 13 cited

Addressing Gap between Training Data and Deployed Environment by On-Device Learning

Kazuki Sunaga, Masaaki Kondo, Hiroki Matsutani

The accuracy of tinyML applications is often affected by various environmental factors, such as noises, location/calibration of sensors, and time-related changes. This article intr…

cs.LG2021

A Low-Cost Neural ODE with Depthwise Separable Convolution for Edge Domain Adaptation on FPGAs

Hiroki Kawakami, Hirohisa Watanabe, Keisuke Sugiura +1

High-performance deep neural network (DNN)-based systems are in high demand in edge environments. Due to its high computational complexity, it is challenging to deploy DNNs on edge…

cs.LG2020

Accelerating ODE-Based Neural Networks on Low-Cost FPGAs

Hirohisa Watanabe, Hiroki Matsutani

ODENet is a deep neural network architecture in which a stacking structure of ResNet is implemented with an ordinary differential equation (ODE) solver. It can reduce the number of…

cs.LG2020

An FPGA-Based On-Device Reinforcement Learning Approach using Online Sequential Learning

Hirohisa Watanabe, Mineto Tsukada, Hiroki Matsutani

DQN (Deep Q-Network) is a method to perform Q-learning for reinforcement learning using deep neural networks. DQNs require a large buffer and batch processing for an experience rep…