Speaker: THAN Quang Khoat, Head of Data Science Lab, HUST
Time & place: Thursday (07/3) afternoon, 2:00 PM in ICTLab meeting room
Title: How to make a machine learn continuously? A tutorial of the Bayesian approach

Abstract: How to build a machine that can continuously learn from observations in its life and make accurate inference/prediction? This is one of the central questions in Artificial Intelligence. Many challenges are present, such as the difficulty of learning from infinitely many observations (data), the dynamic environments, noisy data, the NP-hardness of inference, … This tutorial will discuss how the Bayesian approach can provide an efficient answer. I will start from the basic of Bayesian models, and then the variational Bayes method for inference. Next, we will discuss how to learn a Bayesian model from an infinite sequence of data. Some messages about catastrophic forgetting phenomenon, prior human knowledge, stability-elasticity dilemma, and overfitting will be delivered.