Picture for Hiroki Matsutani

Hiroki Matsutani

ElasticZO: A Memory-Efficient On-Device Learning with Combined Zeroth- and First-Order Optimization

Add code
Jan 08, 2025
Viaarxiv icon

Skip2-LoRA: A Lightweight On-device DNN Fine-tuning Method for Low-cost Edge Devices

Add code
Oct 28, 2024
Figure 1 for Skip2-LoRA: A Lightweight On-device DNN Fine-tuning Method for Low-cost Edge Devices
Figure 2 for Skip2-LoRA: A Lightweight On-device DNN Fine-tuning Method for Low-cost Edge Devices
Figure 3 for Skip2-LoRA: A Lightweight On-device DNN Fine-tuning Method for Low-cost Edge Devices
Figure 4 for Skip2-LoRA: A Lightweight On-device DNN Fine-tuning Method for Low-cost Edge Devices
Viaarxiv icon

A Tiny Supervised ODL Core with Auto Data Pruning for Human Activity Recognition

Add code
Aug 02, 2024
Viaarxiv icon

FPGA-Accelerated Correspondence-free Point Cloud Registration with PointNet Features

Add code
Apr 01, 2024
Figure 1 for FPGA-Accelerated Correspondence-free Point Cloud Registration with PointNet Features
Figure 2 for FPGA-Accelerated Correspondence-free Point Cloud Registration with PointNet Features
Figure 3 for FPGA-Accelerated Correspondence-free Point Cloud Registration with PointNet Features
Figure 4 for FPGA-Accelerated Correspondence-free Point Cloud Registration with PointNet Features
Viaarxiv icon

A Cost-Efficient FPGA Implementation of Tiny Transformer Model using Neural ODE

Add code
Jan 05, 2024
Viaarxiv icon

An FPGA-Based Accelerator for Graph Embedding using Sequential Training Algorithm

Add code
Dec 23, 2023
Viaarxiv icon

An Integrated FPGA Accelerator for Deep Learning-based 2D/3D Path Planning

Add code
Jun 30, 2023
Viaarxiv icon

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

Add code
Dec 19, 2022
Figure 1 for A Sequential Concept Drift Detection Method for On-Device Learning on Low-End Edge Devices
Figure 2 for A Sequential Concept Drift Detection Method for On-Device Learning on Low-End Edge Devices
Figure 3 for A Sequential Concept Drift Detection Method for On-Device Learning on Low-End Edge Devices
Figure 4 for A Sequential Concept Drift Detection Method for On-Device Learning on Low-End Edge Devices
Viaarxiv icon

Communication Size Reduction of Federated Learning based on Neural ODE Model

Add code
Aug 19, 2022
Figure 1 for Communication Size Reduction of Federated Learning based on Neural ODE Model
Figure 2 for Communication Size Reduction of Federated Learning based on Neural ODE Model
Figure 3 for Communication Size Reduction of Federated Learning based on Neural ODE Model
Figure 4 for Communication Size Reduction of Federated Learning based on Neural ODE Model
Viaarxiv icon

An Efficient Accelerator for Deep Learning-based Point Cloud Registration on FPGAs

Add code
Mar 11, 2022
Figure 1 for An Efficient Accelerator for Deep Learning-based Point Cloud Registration on FPGAs
Figure 2 for An Efficient Accelerator for Deep Learning-based Point Cloud Registration on FPGAs
Figure 3 for An Efficient Accelerator for Deep Learning-based Point Cloud Registration on FPGAs
Figure 4 for An Efficient Accelerator for Deep Learning-based Point Cloud Registration on FPGAs
Viaarxiv icon