 When it comes to artificial intelligence, you might think it's a complex subject reserved for massive server and high-tech clouds. But guess what? We have packed machine learning algorithms into an Arduino board to recognize and gesture. So the power of AI is now at your fingertips, quite literally. At ST, we want everyone to be able to release their creativity and we know that running machine learning on Arduino is a great way to achieve that. Here we have an example of an application with Nano AGI Studio running on the SM42 of the Arduino Jigar AR1 because we have to manage the screen and so on. But we have generated such a small model that you can make it run on every microcontroller. As you can see, when I put my hand in front of the time of flight, the model is classifying my gesture in real time. The infamous time is actually 45 microseconds. Then the Arduino Jigar randomly selects a gesture among the possible states and if you're lucky enough, you win the game and you get the gifts. Let's check out or you can do it in a matter of minutes. Let's start by creating a new project and selecting the Arduino board. Allocate the amount of memory that you want to use in the project and select the sensor. Then we can choose between anomaly detection, classification or regression depending on the application we want to target. Let's choose classification and upload our data sets and voila! The studio will find the right model and train it locally. You don't need to be an AI expert to collect massive amount of data and to train the model on a big GPU. This AutoML approach is definitely the easiest way to develop AI library from scratch. Once the benchmark is over and your AI model is ready, you can download the generated library and integrate it into your projects. Of course, if you have chosen an Arduino board, the library will be fully compatible with the Arduino IDE. This model can run on any STM32, even on the smallest Cortex-M0 based or on the famous Arduino Uno. Indeed, here the AI model reach more than 99% of balanced accuracy with a size of 100 kilowatts of flash and less than 1 kilowatt of RAM. By the way, you can easily recreate this application at home by clicking the tutorial link here or here or in the description depending on the editor mode. Running AI on the edge provides incredible value for a lot of applications such as predictive maintenance on electrical motors or activity recognition on smartwatches, just with some of them. You can create new exciting features without any additional infrastructure costs. This is just one use case among millions, so I hope this video gives you some idea for exciting applications you can create thanks to AI solutions from ST. You can try the studio from today, find your favorite Arduino board and start building your application for free. Thanks for watching, take care.