Enabling ultra-low Power Machine Learning at the Edge
tinyML Foundation is a non-profit professional organization focused on supporting and nurturing the fast-growing branch of ultra-low power machine learning technologies and approaches dealing with machine intelligence at the very edge of the cloud. These integrated “tiny” machine learning applications require “full-stack” (hardware, system, software, and applications) solutions including machine learning architectures, techniques, tools, and approaches capable of performing on-device analytics. A variety of sensing modalities (vision, audio, motion, environmental, human health monitoring, etc.) are used with extreme energy efficiency, typically in the single milliwatt (and below) power range, to enable machine intelligence right at the boundary of the physical and digital worlds.
We see a new world with trillions of distributed intelligent devices enabled by energy efficient machine learning technologies that sense, analyze, and autonomously act together to create a healthier and more sustainable environment for all
To enable this vision, tinyML Foundation is:
During this period when we are all working remotely and cannot attend live events, to keep the momentum going the tinyML Foundation is excited to be offering a new activity to our community: tinyML Talks webcast series. A strong line-up of speakers making 30-minute presentations will take place twice a month on Tuesdays at 8 am Pacific time to make sure that tinyML enthusiasts worldwide will have an opportunity to watch them live. Presentations and videos will be available online the day afterwards for those that were not able to join live.
If you want to re-watch all talks starting March 31 or were unable to join us live, the slides and links to our YouTube Channel of the talks are posted at our tinyML Forums. Many questions were asked during the presentations but not all could be answered in the allotted time frame. The answers to some of those can be found on the tinyML Forums as well.
If you have suggestions or ideas for topics of discussion or proposal for tinyML Talks, please contact the Talks team at talks@tinyML.org.
Sponsorship opportunities are available
With over 500 people who joined our first Talk, have seen the numbers grow rapidly. Please see our sponsorship opportunities – among many other benefits all sponsors will be recognized on our website and to thousands e-mail list multiple social media groups.
Please contact Bette Cooper at email@example.com or call 650-714-1570 if you have any questions or need more information.
We are pleased to introduce a new online discussion group, the tinyML Forums, a place to discuss tinyML events and activities along with general discussions of ultra-low power machine learning technology and applications. All are welcome – from newbies to experts in machine learning. This includes hardware architects, software engineers, systems engineers, ASIC designers, algorithms and application developers, low power sensor providers and end users. Further discussions on our tinyML Talks are continued there as well.
We have several live events planned for the rest of 2020 and 2021:
Sponsorship opportunities for the Summit are now available; attendee registration will open in the early fall timeframe.
For further information or if you have any questions please contact: Bette Cooper at firstname.lastname@example.org or +1 650-714-1570.
Our first Meetup group was formed in the Bay Area in June 27, 2019. We now have twenty groups in twenty countries, with over 2,400 members. Visit our Global Meetup site for details.
2019 slides and videos are listed here. For 2020 presentations visit tinyML Talks.
There were two on September 26, one in the Silicon Valley, the other in Austin, TX. Links to the slides, and a video link for the Silicon Valley meeting.
Held at Qualcomm in Santa Clara and attended by over 100 people, we had two speakers – click on title for slides:
Our first meetup was held on June 27 at Qualcomm and was a great success. Over 130 people were in attendance. Below are the presentations and a video file:
Neural networks are getting smaller. Much smaller. The OK Google team, for example, has run machine learning models that are just 14 kilobytes in size—small enough to work on the digital signal processor in an Android phone. With this practical book, you’ll learn about TensorFlow Lite for Microcontrollers, a miniscule machine learning library that allows you to run machine learning algorithms on tiny hardware.
read full description
Evgeni Gousev of Qualcomm and Pete Warden of Google participated in a panel at Stanford University seminar "Current Status of tinyML and the Enormous Opportunities Ahead".
read full article
When the TinyML group recently convened its inaugural meeting, members had to tackle a number of fundamental questions, starting with: What is TinyML? TinyML is a community of engineers focused on how best to implement machine learning (ML) in ultra-low power systems. The first of their monthly meetings was dedicated to defining the issue.
read full article
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