Week 41 Constructing a Neural Network code, Tensor flow and start Convolutional Neural Networks

 

 

 

The Mathematics of Neural Networks

Text will be added here, see handwritten notes for Friday October 15. They contain a discussion on

  1. Activation functions and vanishing gradients
  2. Brief summary of gradient methods
  3. Approximation theorems, in particular the universal approximation theorem for neural networks by Cybenko and Hornik
I strongly recommend Michael Nielsen's intuitive approach to the neural networks and the universal approximation theorem, see the slides at http://neuralnetworksanddeeplearning.com/chap4.html.