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.


information to come





March 19 (Tuesday) Location: TBA

  • 6:30 pm - 8:00 pm

    VIP Reception (venue and details to follow) Committee Members, Speakers, Sponsors

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

  • 7:30 am - 8:30 am

    Registration and Breakfast
  • 8:30 am - 8:45 am

    Welcome and Opening Remarks
  • 8:45 am - 10:45 am

    Hardware and Architectures

    From Small to Tiny: How to Co-design ML Models, Computational Precision and Circuits in the Energy-Accuracy Trade-off Space.Prof. Marian Verhelst, MICAS laboratories (MICro-electronics And Sensors), Electrical Engineering Department, KU Leuven

    The Next Level of Energy-efficient Edge Computing.Simon Craske, ARM Fellow and Lead Embedded Architect, ARM

    Key Challenges Encountered in Inference Engine Design.Sriraman Chari, Senior Design Engineering Group Director, Cadence Design Systems Inc.

    Ultra Low Power Inference at the Very Edge of the Network.Eric Flamand, CTO, Greenwaves Technologies

    Presentation topic to be announced.Cormac Brick, Director of Embedded Machine Intelligence, Intel

    What Can In-memory Computing Deliver, and What Are the Barriers?Prof. Naveen Verma, Princeton University

  • 10:45 am - 11:00 am

  • 11:00 am - 12:40 pm

    Systems and Algorithms

    Better Learning Through SpecializationBill Chappell, Microsystems Technology Office (MTO), Office Director, DARPA

    Ultra-low Always-On Computer VisionEdwin Park, Principal Engineer, Qualcomm

    Machine Learning Accelerators for IoT2 Devices Prof. Dennis Sylvester, Electrical Engineering and Computer Science, University of Michigan

    Next Frontier in CMOS Imaging – Always ON SensingCharles Chong, Director, PixArt Imaging

    Efficient Voice Trigger Detection for Low Resource HardwareKisun You, Senior Realtime Software Engineer, Siri Speech, Apple

  • 12:40 pm - 2:30 pm

    Lunch, Poster Session, Demos, Networking
  • 2:30 pm - 4:30 pm

    Software and Applications

    ELL: the Microsoft Embedded Learning LibraryByron Changuion, Principal Engineering Manager, Machine Learning and Optimization Group Microsoft Research AI

    TF-lite for tinyMLPete Warden, Technical Lead, TensorFlow Mobile and Embedded Team, Google

    Visual AI in Milliwatts: A Grand Challenge and a Massive OpportunityJeff Bier, Founder, Embedded Vision Alliance

    Ultra-Low-Power Command Recognition for Ubiquitous DevicesChris Rowen, CEO, BabbleLabs

    Life on the Edge: Using Embedded AI with Sensor Data to Create ProductsJeff Sieracki, Co-founder and CTO, Reality AI

    Transforming Epilepsy from a Chronic Condition Towards an Acute One Using tinyMLHans DeClerq, CTO, Byteflies

  • 4:30 pm - 6:30 pm

    Reception, Poster Session / Demos, Networking
  • 6:30 pm

    Dinner (at Google)

March 21 (Thursday) Location: 1200 Crittenden Lane, Mountain View, CA

  • 8:00 am - 9:00 am

    Breakfast / Networking
  • 9:00 am - 11:00 am

    Working group and panel discussion sessions

    Hardware and Architectures

    System and Algorithms

    Software and Application

  • 11:00 am - 11:30 am

  • 11:30 am - 12:30 pm

    Concluding Session: tinyML "State-of-the-Union" and Calls to Action
  • 12:30 pm

    Lunch / Networking

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


There have been no room block arrangements at any hotel. The types and prices of properties vary greatly depending on what are you choose to stay. This link will provide you with many choices. For the week of March 18 the prices range from $130 to $600. On the left of the listings you may filter to put in your minimum/maximum price range, cancellation policies, etc.


Venue Map


111 W. Java,
Sunnyvale, CA