Introduction Machine Learning - 3PMEIMLE

Goal(s)

This course is an introduction to artificial intelligence and machine learning: it presents the main features of supervised and unsupervised learning, whether regression or classification. Its objective is to present basic methods and algorithms. By the end of this course, students will be able to set up a simple AI chain dedicated to regression or classification and deploy the model on a target device such as a Raspberry Pi.

Content(s)

This course covers:
_ linear regression and polynomial regression;
_ classification using k-NN, k-means, and hierarchical ascending classification (Ward's method);
_ simple neural network architectures (perceptron, multilayer perceptron, convolutional networks).

The importance of training data is also addressed through data bias, model selection, imbalanced classes, cross-validation, etc.

Mathematics fundamentals.
Probability and statistics course.
Continuous-time signal processing course.
Python programming fundamentals.

Test

The final exam for the Machine Learning course is based on written reports that may include multiple-choice questions (session 1 and session 2).

Additional Information