The Cambridge Ellis Unit Seminar Series includes talks by leading researchers in the area of machine learning and AI. Our next speaker will be Dr. Zeynep Akata. Details of her talk can be found below.
Title: “Explainability in Deep Learning Through Communication”
Abstract: Clearly explaining a rationale for a classification decision to an end-user can be as important as the decision itself. Such explanations are best communicated to the user via natural language. In a conversation, communication is most effective if the speaker understands the purpose of the listener. In this talk, I will present my past and current work on Explainable Machine Learning combining vision and language. Focusing on learning simple and compositional representations of images discriminating properties of the visible object and jointly predicting a class label, I will demonstrate how our models explain why the predicted label is or is not chosen for the image as well as how we improve the explainability of deep models via conversations.