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 preparation for deriving the Backprop algorithm as gradient descent in layered networks, including the use of multi-layer perceptrons, supervised learning with sigmoidal output, notation in multilayer perceptrons, gradient descent, calculating the gradient steps, and applying the chain rule for weight updates.