700.340 (24S) Neurocomputing in Robotics and Intelligent Transportation

Sommersemester 2024

Registration possible till
23.05.2024 23:59

First course session
13.04.2024 10:00 - 13:00 Online Off Campus
... no further dates known

Overview

Lecturer
Course title german Neurocomputing in Robotics and Intelligent Transportation
Type Lecture - Seminar (continuous assessment course )
Course model Blended learning course
Online proportion 40%
Hours per Week 2.0
ECTS credits 4.0
Registrations 15 (20 max.)
Organisational unit
Language of instruction English
Course begins on 13.04.2024
eLearning Go to Moodle course
Seniorstudium Liberale Yes

Time and place

List of events is loading...

Course Information

Intended learning outcomes

Recent advancements in machine learning methods based on deep neural networks have led to performance breakthroughs in many fields, especially within transportation systems and autonomous vehicles. This class will explore how these technologies are revolutionizing the fields of robotics and transportation, equipping students with the knowledge to contribute to the advancement of smart navigation systems and the development of autonomous vehicles. 

This class will not only go over the principles of deep learning but also provide students with an understanding of the most recent research in the field. The first part of the class will begin with a high-level introduction to neural models.

After that, the fundamental strategies and cutting-edge methods for constructing, training, and visually depicting different types of deep learning models to:

  1. Develop object, detection, recognition, localization, and segmentation models.
  2. Understand the basics of attention mechanisms in deep learning.
  3. Overcome the "lack of training data" problem using zero and few-shot learning techniques.

Through hands-on projects, participants will also learn to apply deep learning techniques to real-world transportation challenges, preparing them for the future of intelligent mobility and robotic autonomy.

Teaching methodology including the use of eLearning tools

The sessions will combine theoretical background, seminars about recent papers and mathematical modeling of deep learning architectures  focusing on convolutionAl neural networks.


Course content

  1. Introduction to machine learning
  2. Shallow Neural Networks And Deep Neural Networks - Overview
  3. Backpropagation algorithm - Overview
  4. Convolutional Neural Networks
  5. Semantic segmentation (U-NET)
  6. Transfer learning
  7. Object localization (YOLO)
  8. Semantic embedding (Overview)
  9. Zero shot learning 
  10. Few shot Learning (Siamese Neural Network)
  11. Attention + transformers 
  12. Application in Robotics and Intelligent Transportation

                          






Prior knowledge expected

Applied Statistics + calculus + coding skills in python 


Literature

Python Machine Learning, 3rd edition. By Raschka & Mirjalili

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

Format 

  • An oral exam using a digital platform (e.g., BBB via Moodle) or a written one.

Scheduling

  • Students will be given a specific time slot at least one week before the exam date.
  •  It is crucial for students to check their technical setup before the exam day to avoid any technical difficulties

Examination topic(s)

  • Review course materials, including lecture notes, readings, and assignments.
  • Think critically about the topics and anticipate potential counterarguments or challenges.


Assessment criteria / Standards of assessment for examinations

Evaluation Criteria

  • Depth of Understanding: Demonstrated thorough comprehension of course content
  • Ability to connect course concepts to real-world applications or personal experiences.

Grading scheme

Grade / Grade grading scheme

Position in the curriculum

  • 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)
        • 700.340 Neurocomputing in Robotics and Intelligent Transportation (2.0h VS / 4.0 ECTS)
          Absolvierung im 2., 3. Semester empfohlen
  • Master's degree programme Information and Communications Engineering (ICE) (SKZ: 488, Version: 15W.1)
    • Subject: Information and Communications Engineering: Supplements (NC, ASR) (Compulsory elective)
      • Wahl aus dem LV-Katalog (Anhang 4) ( 0.0h VK, VO, KU / 14.0 ECTS)
        • 700.340 Neurocomputing in Robotics and Intelligent Transportation (2.0h VS / 4.0 ECTS)
  • Master's degree programme Information and Communications Engineering (ICE) (SKZ: 488, Version: 15W.1)
    • Subject: Technical Complements (NC, ASR) (Compulsory elective)
      • Wahl aus dem LV-Katalog (Anhang 5) ( 0.0h VK, VO, KU / 12.0 ECTS)
        • 700.340 Neurocomputing in Robotics and Intelligent Transportation (2.0h VS / 4.0 ECTS)
  • Master's degree programme Information and Communications Engineering (ICE) (SKZ: 488, Version: 15W.1)
    • Subject: Information and Communications Engineering: Supplements (NC, ASR) (Compulsory elective)
      • Wahl aus dem LV-Katalog (Anhang 4) ( 0.0h VK, VO, KU / 14.0 ECTS)
        • 700.340 Neurocomputing in Robotics and Intelligent Transportation (2.0h VS / 4.0 ECTS)
  • Master's degree programme Information and Communications Engineering (ICE) (SKZ: 488, Version: 15W.1)
    • Subject: Technical Complements (NC, ASR) (Compulsory elective)
      • Wahl aus dem LV-Katalog (Anhang 5) ( 0.0h VK, VO, KU / 12.0 ECTS)
        • 700.340 Neurocomputing in Robotics and Intelligent Transportation (2.0h VS / 4.0 ECTS)
  • Master's degree programme Information and Communications Engineering (ICE) (SKZ: 488, Version: 15W.1)
    • Subject: Autonomous Systems and Robotics: Advanced (ASR) (Compulsory elective)
      • Wahl aus dem LV-Katalog (siehe Anhang 3) ( 0.0h VK, VO / 30.0 ECTS)
        • 700.340 Neurocomputing in Robotics and Intelligent Transportation (2.0h VS / 4.0 ECTS)
  • Master's degree programme Information and Communications Engineering (ICE) (SKZ: 488, Version: 22W.1)
    • Subject: Information and Communicatons Enginnering: Supplements (Compulsory elective)
      • 1.3b Ausgewählte Lehrveranstaltungen (siehe Curriculum Seite 16) ( 0.0h VC, KS / 14.0 ECTS)
        • 700.340 Neurocomputing in Robotics and Intelligent Transportation (2.0h VS / 4.0 ECTS)
  • Master's degree programme Information and Communications Engineering (ICE) (SKZ: 488, Version: 22W.1)
    • Subject: ICE- Supplements (Compulsory elective)
      • 2.3b Ausgewählte Lehrveranstaltungen (siehe Curriculum Seite 18) ( 0.0h VC, KS / 14.0 ECTS)
        • 700.340 Neurocomputing in Robotics and Intelligent Transportation (2.0h VS / 4.0 ECTS)

Equivalent courses for counting the examination attempts

Sommersemester 2023
  • 700.340 VS Machine Learning in Intelligent Transportation (2.0h / 4.0ECTS)
Sommersemester 2022
  • 700.340 VS Machine Learning in Intelligent Transportation (2.0h / 4.0ECTS)
Sommersemester 2021
  • 700.340 VS Machine Learning in Intelligent Transportation (2.0h / 4.0ECTS)
Sommersemester 2020
  • 700.340 VS Machine Learning in Intelligent Transportation (2.0h / 4.0ECTS)
Sommersemester 2019
  • 700.340 VS Machine Learning in Intelligent Transportation (2.0h / 4.0ECTS)
Sommersemester 2018
  • 700.340 VS Machine Learning in Intelligent Transportation (2.0h / 4.0ECTS)
Sommersemester 2017
  • 700.340 VS Machine Learning in Intelligent Transportation (2.0h / 4.0ECTS)
Sommersemester 2016
  • 700.340 VS Machine Vision in Intelligent Transportation (2.0h / 4.0ECTS)
Sommersemester 2015
  • 700.340 VS Machine Vision in Intelligent Transportation (2.0h / 4.0ECTS)
Sommersemester 2014
  • 700.340 VS Machine Vision in Intelligent Transportation (2.0h / 4.0ECTS)
Sommersemester 2013
  • 700.340 VS Machine Vision in Intelligent Transportation (2.0h / 4.0ECTS)