Cover Image for Alternative & Frontier Compute
Cover Image for Alternative & Frontier Compute
Avatar for Tokyo AI (TAI)
Presented by
Tokyo AI (TAI)
Hosted By

Alternative & Frontier Compute

Register to See Address
Tokyo
Registration
Approval Required
Your registration is subject to host approval.
Welcome! To join the event, please register below.
About Event

Theme: “Alternative Compute Paradigms for an AI-Driven Future”

Expected topics

  1. Probabilistic & Neuromorphic Compute: Emerging architectures inspired by biology.

  2. Thermodynamic & Physical Computing: Analog computing, optical compute paths.

  3. Bio-Inspired & Bio-Integrated Systems: DNA computing, neural substrate systems.

  4. Future Roadmaps for Post-Moore AI Hardware


Agenda

18:00 Doors open

18:30 - 18:50 Talk 1

18:50 - 19:10 Talk 2

19:10 - 19:30 Talk 3

19:30 - 19:50 Talk 4

19:50 - 20:00 Buffer

20:00 - 21:00 Networking & Food & Drinks

21:00 Doors close

Speakers

Talk 1 - Cross Labs (bio-based / bio-inspired computational substrates)

Speaker: Alyssa Adams

Abstract: TBC

Bio: TBC

Talk 2 - Ceremorphic (energy-efficient supercomputers)

Speaker:

Abstract: Karthik Rampalli

Bio: TBC

Talk 3 - TBC

Speaker: TBC

Abstract: TBC

Bio: TBC

Talk 4 - Introduction of Floadia and Chip-in-Memory (CiM) Technology

Speaker: Hideki Yoneda

Abstract: AI datacenters consume larger amounts of power. With the expansion of AI datacenters, this issue will be a huge issue for the world. NPUs are being developed with 1/3 or 1/5 power consumption compared to NVIDIA GPU, but a 1/3 or 1/5 power consumption reduction cannot solve this issue. Floadia is developing the new AI analog calculation approach in flash memory technology with 1/1000 power. This approach will bring a large power reduction. It is the final solution for this issue.

 Floadia is developing an analog CiM (Computing in Memory) based on SONOS NOR flash memory. This is the super low power analog matrix calculation engine using NOR flash memory array with about 1/1000 power and a lot less than 1/10 cost to NVIDIA GPU. Floadia went through several test chips. Device-level development is complete. 1/1000 power is not possible with a digital way. Most of the NPU power would be 1/3 ~ 1/5. There are several companies that are developing analog CiM. No other companies achieved a 1/1000 level of power and good precision of analog calculation. The Floadia team achieved precise control of electron injection to the SiN layer based on solid-state physics and precise process control. These are very difficult.

Bio: A high energy and visionary person with successful track record in both development and sales/marketing and management of large organization in the US in semiconductor companies. Has a lot of not only knowledge on semiconductor business, semiconductor IP but also telecom technology, industrial technology, and consumer products. Good at creating and maintaining good customer relationship. Have long term vision and strategy creation capability, which increased the company revenue. Have business administration knowledge and skills acquired through experience at Boston Consulting Group, world top level business consulting firm. Have very wide knowledge on science and technology not only semiconductor technology but also any kind of state-of-arts technologies including AI and artificial neural networks, which is very important for strategic marketing for high technology industries. Can understand technologies necessary to the end applications and create strategies/development plan/business plan for the company quickly and produce revenue and profit. Have strong insight to find out business opportunities and structure and lead R&D to create new technology to differentiate the company. Understand cultural difference through the experience to manage the organization in Silicon Valley that consist of people from various countries. My knowledge base, capability to understand new technologies, and insight to find out business opportunities are suitable to making M&A strategy.

Bio: TBC

Talk 5 - Quantum Brilliance (diamond-based quantum devices)

Speaker: Hideaki Yoshimura

Abstract: TBC

Bio: TBC

Organizers

​​​​Ilya Kulyatin: Fintech and AI entrepreneur with work and academic experience in the US, Netherlands, Singapore, UK, and Japan, with an MSc in Machine Learning from UCL.

Supporters

​​Tokyo AI (​​​TAI) is the biggest AI community in Japan, with 4,000+ members mainly based in Tokyo (engineers, researchers, investors, product managers, and corporate innovation managers).

Value Create is a management advisory and corporate value design firm offering services such as business consulting, education, corporate communications, and investment support to help companies and individuals unlock their full potential and drive sustainable growth.

​Privacy Policy

​We will process your email address for the purposes of event-related communications and ongoing newsletter communications. You may unsubscribe from the newsletter at any time. Further details on how we process personal data are available in our Privacy Policy.

Location
Please register to see the exact location of this event.
Tokyo
Avatar for Tokyo AI (TAI)
Presented by
Tokyo AI (TAI)
Hosted By