Introduction to Machine Learning

Lecture 1

• What is machine learning?

• Exemples of problems

• Typology of ML concepts

• Decision tree

• k-NN

Download slides

Readings:

• Chapter 2 in “Machine Learning - A First Course for Engineers and Scientists” (Lindholm, et.)

• The need for biases in learning generalizations (Mitchell)

Lecture 2

• Linear models

• Loss functions

• Regularizaton

Download slides (part 1) Download slides (part 2)

Readinng:

• Chapter 3 in “Machine Learning - A First Course for Engineers and Scientists” (Lindholm, et.)

To go further:

• Optimization with Sparsity-Inducing Penalties (Bach et al.)

Lecture 3

• Deep learning

• Multilayer Perceptron (MLP)

• Convolutional neural networks (CNN)

• Regularization

• Training

Download slides (part 1) Download slides (part 2)

Representation learning visualization

Lecture 4

• Download slides (empirical risk minimization)

• Download slides (clustering)