Zobrazeno 1 - 10
of 172
pro vyhledávání: '"Matsutani, Hiroki"'
Autor:
Matsutani, Hiroki, Marculescu, Radu
In this paper, we introduce a low-cost and low-power tiny supervised on-device learning (ODL) core that can address the distributional shift of input data for human activity recognition. Although ODL for resource-limited edge devices has been studied
Externí odkaz:
http://arxiv.org/abs/2408.01283
Autor:
Sugiura, Keisuke, Matsutani, Hiroki
Point cloud registration serves as a basis for vision and robotic applications including 3D reconstruction and mapping. Despite significant improvements on the quality of results, recent deep learning approaches are computationally expensive and powe
Externí odkaz:
http://arxiv.org/abs/2404.01237
Transformer has been adopted to a wide range of tasks and shown to outperform CNNs and RNNs while it suffers from high training cost and computational complexity. To address these issues, a hybrid approach has become a recent research trend, which re
Externí odkaz:
http://arxiv.org/abs/2401.02721
A graph embedding is an emerging approach that can represent a graph structure with a fixed-length low-dimensional vector. node2vec is a well-known algorithm to obtain such a graph embedding by sampling neighboring nodes on a given graph with a rando
Externí odkaz:
http://arxiv.org/abs/2312.15138
Federated learning is a distributed machine learning approach where local weight parameters trained by clients locally are aggregated as global parameters by a server. The global parameters can be trained without uploading privacy-sensitive raw data
Externí odkaz:
http://arxiv.org/abs/2307.06561
Autor:
Sugiura, Keisuke, Matsutani, Hiroki
Path planning is a crucial component for realizing the autonomy of mobile robots. However, due to limited computational resources on mobile robots, it remains challenging to deploy state-of-the-art methods and achieve real-time performance. To addres
Externí odkaz:
http://arxiv.org/abs/2306.17625
Autor:
Yamada, Takeya, Matsutani, Hiroki
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 phenomenon is known as a concept drift, and this gap degrades the performa
Externí odkaz:
http://arxiv.org/abs/2212.09637
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 are shared between them without uploading raw data to the server. There
Externí odkaz:
http://arxiv.org/abs/2208.09478
Autor:
Sugiura, Keisuke, Matsutani, Hiroki
Point cloud registration is the basis for many robotic applications such as odometry and Simultaneous Localization And Mapping (SLAM), which are increasingly important for autonomous mobile robots. Computational resources and power budgets are limite
Externí odkaz:
http://arxiv.org/abs/2203.05763
Publikováno v:
IEEE Micro (2023)
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 introduces a neural network based on-device learning (ODL) approach to add
Externí odkaz:
http://arxiv.org/abs/2203.01077