tinyML Summit

Advances in ultra-low power Machine Learning technologies and applications

March 20-21, 2019

Sunnyvale, California

About the Summit

Bringing Machine Learning (ML) to the very "edge" of the physical world where sensing and data collection take place is a major trend in the coming era of machine intelligence. This is also fueled by new use cases and applications and significant economic value creation across numerous platforms and industries.

Based on the progress to-date, there are strong reasons to believe that the future of ML will be "tiny". Whereas cloud-based machine learning evolves at an astronomic pace, development and deployment of ML at the very edge remains a technological challenge constrained by compute, memory, energy, network bandwidth and data privacy and security limitations. This is especially true for battery operated devices and always-on use cases and applications.

The tinyML Summit is a gathering of experts actively working on developing and commercializing Machine Learning for extreme energy efficient applications (on the order of few mW power consumption), designed to help drive the field of smart embedded sensors and systems forward. The Summit will holistically cover all key aspects on tinyML, grouped into the three "pillars": (i) dedicated hardware, (ii) special algorithms and network development and power efficient software, and (iii) ultralow power system designs and sensors of different modalities and applications.

The initial event is for a relatively small group of expert-level attendees from the industry and academia invited based on recommendations and reviews (including poster submissions) by the organizing committee. This diverse group of researches and practitioners will review the state-of-art of tinyML from different angles and work together on setting the directions for the ecosystem and agenda for future Summits.






March 19 (Tuesday) Location: House Family Vineyards

  • 6 pm - 9 pm

    VIP Reception Committee Members, Speakers, Sponsors

March 20 (Wednesday) Location: 111 Java Drive, Sunnyvale, CA

March 21 (Thursday) Location: 111 Java Drive, Sunnyvale, CA

  • 8:00 am - 9:00 am

    Breakfast / Networking
  • 9:00 am - 10:00 am

    tinyML State of Technology: Summary and Highlights of Summit Day 1 to be presented by:

    Hardware and Architectures Ian Bratt

    System and Algorithms Boris Murmann

    Software and Application Kurt Keutzer

  • 10:00 am - 10:30 am

  • 10:30 am - 11:45 am

    Two Panels and Audience Discussions to be moderated by Chris Rowen, Co-founder and CEO, Babblelabs:

    tinyML Applications: opportunities and challenges

    tinyML Ecosystem development

  • 11:45 am - 12:00 pm

  • 12:00 pm - 12:15 pm

    Concluding Remarks – Call to Action
  • 12:15 pm - 1:30 pm


Poster Session

Experts from the industry, academia and government labs (worldwide) actively working in the tinyML field are encouraged to submit a one page abstract in the MS Word and Adobe PDF formats. The abstract should clearly state:

  1. problem to be solved,
  2. technical approach and its novelty,
  3. results,
  4. significance for the tinyML community,
  5. abstract should reflect and highlight TinyML aspects of the work.

Showing demos at the poster session is a plus. Abstracts and poster presentations are considered in the three "pillar" areas: Hardware and Architecture, System and Algorithms, and Software and Applications.

Abstracts will be reviewed by the committee on an ongoing basis (monthly) with the final submission deadline on January 30, 2019. Authors will be notified accordingly during review period.

Please send to bcooper@mepcom.net


Founding Sponsors

Gold Sponsors

Silver Sponsors

Dinner Sponsors


TinyML Sees Big Hopes for Small AI (EE Times)

SUNNYVALE, Calif. – A group of nearly 200 engineers and researchers gathered here to discuss forming a community to cultivate deep learning in ultra-low power systems, a field they call TinyML. In presentations and dialogs, they openly struggled to get a handle on a still immature branch of tech’s fastest-moving area in hopes of enabling a new class of systems.

read full article