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 explores the landscape, performance, and curse of dimensionality in deep learning, discussing the challenges of classifying data in large dimensions, the principles of deep learning, the geometry of loss landscape, overfitting phenomena, and the impact of dimensionality on learning. It also delves into the concepts of locality, hierarchy, sparsity, and stability in relation to smooth deformations in neural networks.