Doorkeeper

[Succinct Information Team Seminar] On-Device Learning for Edge AI: From Algorithms to Applications

Tue, 31 Mar 2026 15:00 - 16:00 JST
Online Link visible to participants
Register
Free admission

Description

Format: Hybrid

Online Venue: Open to all registered participants. The seminar will be delivered via Zoom. The URL will be provided only to registered participants.

On-site Venue: For RIKEN members only. RIKEN AIP Nihonbashi Office Open Space


Talk Information

Date & Time: March 31 (Tue), 15:00–16:00

Speaker: Hiroki Matsutani (Professor, Department of Information and Computer Science, Faculty of Science and Engineering, Keio University)

Title: On-Device Learning for Edge AI: From Algorithms to Applications

Abstract:

We are working on on-device learning techniques that enable AI models to be trained and adapted directly on resource-constrained edge devices. Such on-device learning is particularly effective when there is a discrepancy between pre-collected training data and data observed in real-world environments. A key advantage is the ability to update models in situ to accommodate environmental changes and individual differences. In recent years, AI chips equipped with on-device learning capabilities have emerged, and commercialization and mass production are progressing. In this talk, we will introduce on-device learning from its underlying algorithms to practical application examples.

About this community

RIKEN AIP Public

RIKEN AIP Public

Public events of RIKEN Center for Advanced Intelligence Project (AIP)

Join community