Introducing Machine Learning Concepts by Training a Neural Network to Recognize Hand Gestures

We present an foreground); show that rotation of the hand is arbitrary, the interactive, guided experimental activity which assumes no background may be uneven, lighting and subjects are heterogeneous background knowledge, during which the audience is introduced (adults and kids, male and female, different skin to supervised deep learning and some of its core concepts colors). in a learning-by-doing fashion. The activity consists in 3. In order to train a classifier, we need a training dataset, building from scratch a system that solves a challenging visual which we don't yet have: so we ask the audience to acquire pattern recognition task, namely classifying "rock paper it. We underline that for each picture they shoot we need scissors" hand gestures from pictures; the process encounters to know the class, and in practice we want to end up with unanticipated setbacks and challenges, which prompt three folders full of pictures, one for each.