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 challenges in deep learning and machine learning applications, including surveillance, privacy, manipulation, psychographics, political and societal concerns, fairness, interpretability, energy efficiency, cost, parameter estimation, risk estimation, Rademacher complexity, and generalization error. The instructor discusses theoretical challenges, generalization bounds, Rademacher complexity, energy efficiency, and the correlation between complexity measures and generalization in deep learning.