Machine Learning for Physicists (Lecture 3): Training networks, Keras, Image recognition

Contents: extended review of previous material, training a 2D function (reproducing an arbitrary image), first steps towards analyzing and interpreting a neural network, influence of batch size and learning rate, brief introduction to the keras package and its basic neural network routines, image recognition (one-hot-encoding, softmax, cross-entropy), the danger of overfitting, training vs. validation vs. test data

Lecture series by Florian Marquardt: Introduction to deep learning for physicists. The whole series covers: Backpropagation, convolutional networks, autoencoders, recurrent networks, Boltzmann machines, reinforcement learning, and more.