Data & AI

Mathematics for Machine Learning

This course provides a solid foundation in the mathematical concepts essential for understanding and implementing machine learning algorithms. It begins with the fundamentals of vectors, matrices, and linear systems, which are crucial for data representation and manipulation. The course then explores differential calculus and partial derivatives, key for optimization techniques used in machine learning. Participants will also learn about optimization methods such as gradient descent, which is central to many machine learning algorithms. Additionally, the course covers regularization and cost functions, helping learners understand how to improve model performance and avoid overfitting. Throughout, the course emphasizes practical applications and provides examples to solidify understanding.

Content
  • Vectors, Matrices, and Linear Systems: Introduction to vectors and matrices, basic operations, and solving linear systems. Applications to data representation and manipulation
  • Differential Calculus and Partial Derivatives: Basic principles of differential calculus, focusing on partial derivatives, gradients, and their use in optimization
  • Optimization Techniques: Overview of optimization methods, with a focus on gradient descent and its role in machine learning models
  • Regularization and Cost Functions: Introduction to regularization techniques to prevent overfitting, and understanding cost functions for model evaluation and improvement
Learning Outcomes

By the end of this course, participants will be able to: 

  • Understand and apply the basic concepts of vectors, matrices, and linear systems in machine learning
  • Compute and interpret partial derivatives and gradients for optimization tasks
  • Apply optimization techniques, including gradient descent, to minimize cost functions
  • Recognize and implement regularization techniques to improve model generalization and prevent overfitttng
Training Method

The course follows a traditional classroom format with slide presentations, fostering interactive engagement and active participation.

Certification
Certificate of Participation
Prerequisites

There are no prerequisites


Planning and location
Session 1
06/11/2025 - Thursday
10:00 - 17:30
Session 2
07/11/2025 - Friday
10:00 - 17:30
Learning Track

This course is part of the following learning track(s) and can be booked as a stand-alone training or as part of a whole:

ESCO Occupations
Available Edition(s):

https://www.dlh.lu/web/image/product.template/1889/image_1920?unique=d71c149

This combination does not exist.

48.00 € 48.0 EUR 48.00 €

48.00 €

Not Available For Sale

Your trainer(s) for this course
Angelo Koudou
Angelo Koudou
View all their courses.

Angelo Koudou is a senior lecturer in mathematics, specializing in statistics and probability. His research focuses on the analysis of statistical distributions and their applications in data science.