Together with Hackster, we hosted a webinar on our new Edge Optimized Neural (EON™) compiler that will kick your TinyML code into overdrive.
As recently announced, EON™ runs a neural network in 25-55% less RAM and up to 35% less flash while retaining the same accuracy, compared to TensorFlow Lite for Microcontrollers. EON™ achieves this magic by compiling your neural networks to C++, unlike other embedded solutions using generic interpreters, thus eliminating complex code, device power, and precious time.
The webinar gave a peek at the capabilities of the new neural complier and a chance to see it in action during a live demo. Watch the video above and you'll learn:
- What is EON™ and why was it built?
- How to compile neural networks to C++ in record speed and (smaller) size.
- How vibration, audio, vision, or your own sensors work with EON™.