Introduction to Deep Learning
Lecture 1: image statistics & sparse coding
Lecture 2: Maximum Entropy, FRAME model, MCMC
Lecture 3: Distributed Representations, Boltzmann Machines
Lecture 4: Variational Inference, Mean Field Theory
Lecture 5: Deep Belief Networks
Lecture 6: Optimisation for Deep Learning (incomplete slides) additional notes
Lecture 7: Convolutional Nets, Dropout, Maxout
Lecture 8: Object Detection and Beyond
Lab assignments
Back to all courses