Program Overview

Program Details

The provided markdown content contains information about a university program, specifically the "Fundamentals of machine learning" course. Below are the extracted program details in a structured markdown format.

Course Overview

The "Fundamentals of machine learning" course is a 4-credit course taught by Liebling Michael Stefan Daniel in French. The course provides an overview of machine learning techniques, including algorithms, theoretical formalism, and experimental protocols.

Course Content

The course covers the following topics:

• Introduction to machine learning
• Linear and logistic regression, gradient descent
• Support vector machines, kernel methods
• Bias-variance dilemma, over- and under-learning
• Dimensionality reduction methods, PCA
• Clustering methods, nearest neighbors method
• Decision trees, ensemble methods, bagging, boosting
• Artificial neural networks, multilayer perceptron
• Convolutional and deep neural networks
• Density estimation, maximum likelihood, Bayesian inference, expectation-maximization learning
• Meta-parameter estimation and experimental protocols
• Societal, ethical, and legal implications of artificial intelligence

Course Objectives

By the end of the course, students should be able to:

• Recognize different types of machine learning
• Understand the functioning, application domain, and limitations of various machine learning algorithms
• Identify appropriate methods for practical problems and formalize their expression
• Implement machine learning algorithms
• Recognize the limitations and ethical implications of machine learning

Course Requirements

The course requires the following prerequisites:

• Analysis (differential and integral calculus)
• Linear algebra
• Probabilities and statistics

Teaching Method

The course is taught through:

• Lectures
• Exercise-lab sessions (combination of theoretical exercises and computer applications/programming)

Evaluation Method

The course is evaluated through:

• A series of weekly exercises (15%)
• A final exam (85%)

Resources

The course uses the following resources:

• "Introduction to Machine Learning" by Chloé-Agathe Azencott (book)
• Electronic resources available on Moodle

Programs

The "Fundamentals of machine learning" course is part of the following programs:

• Electrical and Electronics Engineering (Bachelor semester 6)
• Financial engineering (Master semester 2 and 4)
• Management, Technology and Entrepreneurship (Master semester 2 and 4)
• Passerelle HES - EL (Spring semester)

Reference Week

The course schedule is as follows: | Time | Mo | Tu | We | Th | Fr | | --- | --- | --- | --- | --- | --- | | 8-9 | | | | | | | 9-10 | | | | | | | 10-11 | | | | | | | 11-12 | | | | | | | 12-13 | | | | | | | 13-14 | | | | | | | 14-15 | | | | | | | 15-16 | | | | | | | 16-17 | | | | | | | 17-18 | | | | | | | 18-19 | | | | | | | 19-20 | | | | | | | 20-21 | | | | | | | 21-22 | | | | | |