Are you an EPFL student looking for a semester project?
Work with us on data science and visualisation projects, and deploy your project as an app on top of Graph Search.
This lecture covers the concept of bagging as a regularization method in deep learning, where multiple variants of a model are trained on different subsets of data to improve generalization. The instructor explains the bagging algorithm, how each model can be a deep network, and how the models see different data sets. The lecture also includes a quiz on the benefits of averaging predictions over multiple models in machine learning competitions.