AutoML

Overview

Semester Winter 
ECTS 5
Level Master

Description

Language

The course will be held in English.

Machine Learning (ML) has achieved remarkable success in recent years. However, the choice of ML algorithms (SVM, random forest, or deep neural network) and their hyper-parameters is yet another process of “learning” e.g., designing a well-performed ML system requires a lot of expert knowledge, and it is often the result of repeated “trial and error”. Even worse, the “no free lunch” theorem indicates that there is no single approach that works best across every task. Hence, the above tedious process will be repeated and faced with new tasks. To alleviate the above problems, Automated Machine Learning (AutoML) is proposed to automate the design of the whole ML pipeline, including but not limited to the techniques mentioned above. In this practical lab course, you will learn to implement the main ideas of an AutoML system from scratch and how to apply AutoML to applications.

Recommended pre-requisites

  • Machine Learning
  • Deep Learning

Lecturer

Prof. Dr. rer. nat. Marius Lindauer
Address
Welfengarten 1
30167 Hannover
Building
Room
Prof. Dr. rer. nat. Marius Lindauer
Address
Welfengarten 1
30167 Hannover
Building
Room

Topics

  • Diving deeper into AutoML 
  • Implementation of different AutoML approaches
  • Hands-on experiences with AutoML packages

Literature

There is no recommended literature for this course.

Online Courses

AutoML - Automated Machine Learning