RWTHx: Basics of Machine Learning

Back to Results (neural networks)

RWTHx: Basics of Machine Learning

by RWTH Aachen University

The "Basics of Machine Learning" course offered by RWTHx provides a comprehensive dive into the essential elements of machine learning. It equips participants with knowledge on diverse topics, including but not limited to probability density estimation, various regression techniques, linear discriminants, support vector machines, as well as ensemble methods. Moreover, the course introduces participants to the foundational aspects of deep neural networks which are pivotal for advanced studies in the field.

Core definitions and principles of statistical machine learning.
Understanding and application of different probability density estimation techniques.
Formulation and usage of linear discriminant models for classification tasks.
Development of regression models including linear and logistic regression.
Practical understanding of Support Vector Machines.
Introduction to ensemble methods like bagging and boosting, with a hands-on approach.
Foundational knowledge of neural networks, suitable for ensuing advanced learning.

Before enrolling in this course, students should have:

A basic understanding of linear algebra (vectors, matrices).
Fundamental knowledge of stochastics and statistics (mean, variance, random variables, normal distribution).
Elementary programming skills, preferably in Python.

Statistical Machine Learning Definitions
Probability Density Estimations
Linear and Logistic Regression Models
Support Vector Machines
Ensemble Methods Introduction
Basics of Neural Networks

This course is designed for individuals who are:

Intermediate-level participants interested in machine learning.
Professionals seeking to deepen their understanding of machine learning techniques.
Students who have a background in statistics, stochastics, and programming, looking to advance their career in machine learning or related fields.

The skills acquired in this course can be applied in a variety of real-world scenarios, such as: