François Chung, Ph.D.

Tag: gradient descent

Neural networks and deep learning

Neural networks and deep learning

Coursera training, MOOC (2018). Given online by Stanford University (US), this training introduces the foundations of deep learning. Main objectives are to understand the major technology trends driving deep learning, be able to build, train, apply and implement fully connected deep neural networks, and understand their key parameters. The training aims to teach how deep learning actually works, rather than presenting only a surface-level description.

Week 1: Introduction to deep learning

Main topics:

  • What is a neural network?
  • Supervised learning with neural networks;
  • Why is deep learning taking off?

Week 2: Neural networks basics

Main topics:

  • Binary classification;
  • Logistic regression;
  • Gradient descent;
  • Derivatives with a computation graph;
  • Vectorizing logistic regression.

Week 3: Shallow neural networks

Main topics:

  • Neural network representation;
  • Computing a neural network's output;
  • Vectorizing across multiple examples;
  • Activation functions and their derivatives;
  • Gradient descent for neural networks;
  • Random initialization.

Week 4: Deep neural networks

Main topics:

  • Multilayer neural network;
  • Forward and backward propagation;
  • Building blocks of deep neural networks;
  • Parameters vs hyperparameters.

Reference

Related articles

Learn more