collaborators

5 papers

cs.LG2025

InstantFT: An FPGA-Based Runtime Subsecond Fine-tuning of CNN Models

Keisuke Sugiura, Hiroki Matsutani

Training deep neural networks (DNNs) requires significantly more computation and memory than inference, making runtime adaptation of DNNs challenging on resource-limited IoT platfo…

cs.LG2025

PointODE: Lightweight Point Cloud Learning with Neural Ordinary Differential Equations on Edge

Keisuke Sugiura, Mizuki Yasuda, Hiroki Matsutani

Embedded edge devices are often used as a computing platform to run real-world point cloud applications, but recent deep learning-based methods may not fit on such devices due to l…

cs.LG2025

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

Keisuke Sugiura, Hiroki Matsutani

Zeroth-order (ZO) optimization is being recognized as a simple yet powerful alternative to standard backpropagation (BP)-based training. Notably, ZO optimization allows for trainin…

cs.LG2024

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

Ikumi Okubo, Keisuke Sugiura, Hiroki Matsutani

Transformer has been adopted to image recognition tasks and shown to outperform CNNs and RNNs while it suffers from high training cost and computational complexity. To address thes…

cs.LG2024

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

Kazuki Sunaga, Keisuke Sugiura, Hiroki Matsutani

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…