626.017 (24S) Selected Topics in Machine Learning

Sommersemester 2024

Registration deadline has expired.

First course session
04.06.2024 11:00 - 15:00 S.1.37 On Campus
Next session:
19.06.2024 11:00 - 17:30 S.1.37 On Campus

Overview

Lecturer
Course title german Selected Topics in Machine Learning
Type Lecture - Course (continuous assessment course )
Course model Blended learning course
Online proportion 25%
Hours per Week 2.0
ECTS credits 4.0
Registrations 16 (30 max.)
Organisational unit
Language of instruction Englisch
possible language(s) of the assessment English
Course begins on 04.06.2024
eLearning Go to Moodle course

Time and place

List of events is loading...

Course Information

Teaching methodology including the use of eLearning tools

Lectures, practical exercises, and an optional project possibly chosen by the student and a topic of the student's choice.

Course content

Reinforcement learning

Reinforcement learning is about making sequences of decisions

Stunning achievements of reinforcement learning

How to find good sequences of decisions in an unknown domain through exploration and learning?

Delayed rewards, long-term benefits of decisions, exploration and exploitation

Improving decision policy through exploration

Generalizing what has been learned


Learning from examples and background knowledge

How to use prior knowledge in Machine Learning?

Learning in logic – Inductive Logic Programming (ILP)

Algorithms for learning programs from examples in ILP

Discovering new abstract concepts


Learning qualitative models with applications in robotics

How to model qualitatively, avoiding numbers?

Reasoning and simulation with qualitative models

Learning qualitative models from observations

Learning and planning of robot tasks: rescue robot, cart-pole balancing, humanoid robot, quadcopter


Learning from noisy data

Problems with noise in learning data

Key ideas to cope with noise: simpler models are often better

Algorithms for learning decision trees from noisy data

How to estimate probabilities in machine learning correctly?


Argument-Based Machine Learning (ABML)

Human expert may help learning by annotating training examples with arguments

An algorithm for learning rules from argumented examples


Discovering problem structure with function decomposition

The idea of structuring the learning problem with function decomposition

Discovering structure with HINT algorithm

Improving accuracy and interpretability by structure learning

Examination information

Im Fall von online durchgeführten Prüfungen sind die Standards zu beachten, die die technischen Geräte der Studierenden erfüllen müssen, um an diesen Prüfungen teilnehmen zu können.

Examination methodology

Written exam, possible bonus points for optional project

Examination topic(s)

Content actually covered in lectures

Assessment criteria / Standards of assessment for examinations

Points scored at written exam,  adding bonus points from optional project

Grading scheme

Grade / Grade grading scheme

Position in the curriculum

  • Thematic Doctoral Programme Informatics (SKZ: ---, Version: 17W.1)
    • Subject: Informatics (Compulsory subject)
      • Informatics ( 0.0h XX / 0.0 ECTS)
        • 626.017 Selected Topics in Machine Learning (2.0h VC / 4.0 ECTS)
  • Master's degree programme Informatics (SKZ: 911, Version: 19W.2)
    • Subject: Artificial Intelligence (Compulsory elective)
      • Weitere LVen aus dem gewählten Spezialisierungsfach ( 0.0h XX / 12.0 ECTS)
        • 626.017 Selected Topics in Machine Learning (2.0h VC / 4.0 ECTS)
          Absolvierung im 1., 2. Semester empfohlen
  • Master's degree programme Artificial Intelligence and Cybersecurity (SKZ: 993, Version: 20W.1)
    • Subject: Specialisation in Artificial Intelligence and Cybersecurity (Compulsory elective)
      • Fachlich relevante Lehrveranstaltungen ( 0.0h XX / 34.0 ECTS)
        • 626.017 Selected Topics in Machine Learning (2.0h VC / 4.0 ECTS)
          Absolvierung im 2., 3. Semester empfohlen
  • Doctoral programme Doctoral programme in Technical Sciences (SKZ: 700, Version: 18W.1)
    • Subject: Studienleistungen gem. § 3 Abs. 2a des Curriculums (Compulsory subject)
      • Studienleistungen gem. § 3 Abs. 2a des Curriculums ( 0.0h XX / 32.0 ECTS)
        • 626.017 Selected Topics in Machine Learning (2.0h VC / 4.0 ECTS)

Equivalent courses for counting the examination attempts

Sommersemester 2023
  • 626.017 VC Selected Topics in Machine Learning (2.0h / 4.0ECTS)
Sommersemester 2022
  • 626.017 VC Selected Topics in Machine Learning (2.0h / 4.0ECTS)
Sommersemester 2021
  • 626.017 VC Selected Topics in Machine Learning (2.0h / 4.0ECTS)
Sommersemester 2020
  • 626.017 VC Selected Topics in Machine Learning (2.0h / 4.0ECTS)
Sommersemester 2019
  • 623.131 VC Selected Topics in Artificial Intelligence (2.0h / 4.0ECTS)
Sommersemester 2018
  • 623.131 VC Selected Topics in Machine Learning (2.0h / 4.0ECTS)
Sommersemester 2017
  • 623.131 VC Selected Topics in Artificial Intelligence (2.0h / 4.0ECTS)
Sommersemester 2016
  • 623.131 VC Selected Topics in Artificial Intelligence (2.0h / 4.0ECTS)
Sommersemester 2015
  • 623.131 VK Selected Topics in Artificial Intelligence (2.0h / 4.0ECTS)
Sommersemester 2014
  • 623.131 VK Selected Topics in Artificial Intelligence (2.0h / 4.0ECTS)
Sommersemester 2013
  • 623.131 VK Selected Topics in Artificial Intelligence (2.0h / 3.0ECTS)
Sommersemester 2012
  • 623.131 VK Selected Topics in Artificial Intelligence (2.0h / 3.0ECTS)
Sommersemester 2011
  • 623.131 VK Selected Topics in Artificial Intelligence (2.0h / 3.0ECTS)