It is very important to ensure fairness while building an AI system which can scale to a large number of users. Thus, he will first talk about why fairness is important while building AI apps. He would then go on to talk about how FairLearn helps us in doing so specifically with the easy to use dashboard interface. He will also show how FairLearn could be used to assess the model fairness and how it does so. He would also talk about mitigation strategies with FairLearn so as to remove the biases with state of the art models and compare multiple models to perform this successfully. He will then go on to show live demos about using FairLearn and Azure ML to assess and mitigate fairness in an AI system.
TedX, TedEd Speaker