Filmed at https://2018.dotai.io on May 31st in Paris. More talks on https://www.dotconferences.com/talks During a fictional match between a human and an AI algorithm, Virginie reviews 3 traps to avoid when working with Artificial Intelligence and how to tackle them: the accuracy paradox (when you have imbalanced classes), the choice of the evaluation function in behavioral tasks, and spotting overfitting in behavioral tasks