​Description

​This session looks at how intelligent systems are being built and used in different settings. It covers running AI on small devices and why moving computation from the cloud to the edge matters, using in-memory processing to handle complex biological data faster, and designing lightweight, safety-critical systems for fleets of drones, including communication and AI challenges.

​Agenda

​​18:00 Doors open

​​18:30 - 19:00 From Cloud to Edge: Practical Strategies for Deploying AI on Resource-Constrained Devices (Eldar Sido)

​​19:00 - 19:30 How In-Memory Processing Accelerates Bioinformatics Applications (Syrine Ben Driss)

​​19:30 - 20:00 IoT in the Sky: Designing Lightweight Safety-Critical Systems at Scale (Whitney Huang)

​​20:00 - 21:00 Networking

​​21:00 Doors close

​Speakers:

​Talk 1 - From Cloud to Edge: Practical Strategies for Deploying AI on Resource-Constrained Devices

​Speaker: Eldar Sido

​Abstract: As AI models move closer to sensors and devices, the demand for efficient, private, and low-cost intelligence at the edge has never been stronger. This talk explores why TinyML and Edge AI matter—examining the economic drivers, privacy advantages, reduced latency, and the opportunity to leverage billions of data points generated locally that never reach the cloud. We'll discuss the foundational techniques that enable AI on resource-constrained devices, then dive into real-world deployment examples across predictive maintenance, voice, and vision applications. Attendees will gain insight into why edge AI is reshaping industries and how organizations are successfully implementing these solutions today.

​Bio: Eldar Sido is a Staff AI Product Manager at Renesas Electronics, leading initiatives at the intersection of AI and embedded/edge devices. He drives product strategy for AI compilers, AI enablement tools, and platforms for resource-constrained hardware. With a Master's from the University of Tokyo and experience in edge deployment and AI product evangelism, Eldar focuses on bridging research and real-world embedded AI adoption. He has led initiatives spanning computer vision, voice analytics, and real-time analytics for intelligent edge systems.

​Talk 2 - How In-Memory Processing Accelerates Bioinformatics Applications

​Speaker: Syrine Ben Driss

​Abstract: Biology outpaces the von Neumann machine. This talk dives into how next-gen storage and compute architectures can bridge that gap and make real-time biological insight possible.

​Bio: Syrine Ben Driss is a computer scientist and founder of Operon Technologies (in stealth), where she’s developing next-generation compute architectures for biological data. With experience spanning AI engineering in Japan, software design in Sierra Leone, and entrepreneurship across Africa and Asia.

​Talk 3 - IoT in the Sky: Designing Lightweight Safety-Critical Systems at Scale

​Speaker: Whitney Huang

​Abstract: We know about IoT in our homes...but what about IoT in the sky? This talk explores how a fleet of thousands of drones flying at 100+ km/h maintains communication with the cloud (and each other), and the safety-critical considerations that go into designing a system this complex, all while needing to fit on tiny, lightweight chips. We will also touch on how AI is (and isn't) used onboard this fleet, and why.

​Bio: Whitney Huang is a robotics software engineer passionate about using technology to tackle problems facing humanity. She is a former engineer at Zipline with a BS in Mechanical & Aerospace Engineering from Princeton.

​​​​​​​Tokyo AI (TAI) information

​​​​TAI is the biggest AI community in Japan, with 2,400+ members mainly based in Tokyo (engineers, researchers, investors, product managers, and corporate innovation managers).

​Web: https://www.tokyoai.jp/