We’re beyond thrilled and honored to announce that our Edge Optimized Neural (EON) compiler has been named “Best Innovation of the Year” at this year’s inaugural tinyML Summit Awards.
On behalf of the Edge Impulse team, we would like to thank our entire community, ambassadors, partners, and the tinyML Foundation awards committee for making this all possible. It has been so exciting to see the growth of embedded machine learning and it means a lot to have the recognition of our industry.
Launched late last year, the EON compiler accelerates embedded ML code to run faster on neural networks in 25-55% less RAM and up to 35% less flash, while retaining the same accuracy, compared to TensorFlow Lite for Microcontrollers. It achieves this performance by compiling neural networks to C++, unlike other embedded solutions using generic interpreters, thus eliminating complex code, device power, and precious time.
EON represents the new standard for tinyML developers seeking to bring better embedded technologies to the market. Hear more about it from Daniel Situnayake below, along with the other finalists’ presentations.
The competition was tough, so a well-deserved shoutout goes to our fellow finalist Aspinity for the work they are doing around analog machine learning. Last but not least, a big congrats to “Best Product of the Year” winner Syntiant and their new NDP120 processor.