Tuning model performance with EON Tuner

Developing the most efficient ML pipeline for a given application is always challenging. One way to do this is through iterative experiments. For example, we can evaluate how some target metrics (latency, memory, and accuracy) change depending on the input feature generation and the model architecture. However, this process is time-consuming because there are several combinations, and each one needs to be tested and evaluated. Furthermore, this approach requires familiarity with digital signal processing and NN architectures to know what to tune.

In this recipe, we will use the EON Tuner to find the best ML pipeline for the Arduino Nano.

Getting ready

EON Tuner (https://docs.edgeimpulse.com/docs/eon-tuner) is a tool for automating the discovery of the best ML-based solution for a given target platform. However, it is not just an automated ML (AutoML) tool because the processing block is also part of the optimization problem. Therefore...