The talk is centered around performance optimisations for Edge AI applications. We'll begin with identifying bottlenecks in the inference of machine learning models and move on to ways to handle them. A major part of the solution is in the use of a specialised library like CMSIS-NN (Cortex Microcontroller Software Interface Standard - Neural Network), which provides optimisation for compute-intensive operators targeting Arm Cortex-M processors. Common optimisation methodologies used in CMSIS-NN will also be discussed. We have something for model designers by showing how hyperparameters of operators affect performance and some solutions to handle it.
In the end, Fredrik will give a live demo of CMSIS-NN together with TensorFlow Lite for Microcontrollers showcasing the benefits of optimisation using an Arduino Nano 33 BLE sense board.