Week 08: March 6-March 13

Interactive session, Monday March 13

• Notebook and whiteboard screen shots
  • Updated March 29: plot after SGD and run with 100 hidden nodes

Weekly lecture:

Slides

Video Recordings:

1. Feed-forward neural networks (Multi-layer Perceptrons)
2. Matrix representations
3. The Backpropagation Algorithm
   1. The basic
   2. Linear Regression
   3. The hidden layer
   4. Logistic Regression
   5. Multi-class classification
4. Finer Details
5. Evaluation: Precision and Recall

Readings:

Marsland, Machine Learning

• Ch. 4 "The Multi-layer Perceptron", everything, except
  • (for now) 4.2.6 Picking up momentum
  • the technical details of 4.6 Deriving Back-propagation,
    What you have to know here, is covered by the lectures.

Weekly exercises

• Exercises
• Solutions