Intelligent Systems

Autonomous Learning

 al

 

Lecture (infAuLearn-01a)

2 SWS, ECTS credits: 8
Suitable for ERASMUS / exchange students, language of instruction: English
Time and place: Tuesday 14:15 - 15:45, online
Lecture period sommer term 2021: Tuesday, April 20th, 2021 - Friday, July 9th, 2021
For more information UnivIS

Kick-off meeting for the lecture Autonomous Learning will take place on April 20th 2021 at 02:15 pm via this zoom link. The details for participation as well as for all subsequent dates will be discussed in this event.
 


 

Exercise (EinfAuLearn-01a)

Work sheets containing questions, mathematical tasks, and programming tasks (based on provided Jupyter notebooks)
2 SWS
suitable for ERASMUS / exchange students, language of instruction: English
Time and place: Tuesday 08:30 - 10:00, online
Lecture period sommer term 2021: Tuesday, April 27th, 2021 - Friday, July 9th, 2021
 

Practical Exercise (PEinfAuLearn-01a)

Mandatory programming tasks in a given computer game environment, i.e. application of Reinforcement Learning algorithms to specific problems (to be accomplished by teams of students). There will be approx. four different practical tasks that need to be finished successfully to be allowed to participate in the exam.
2 SWS
suitable for ERASMUS / exchange students, language of instruction: English
Time and place: Wednesday 08:30 - 10:00, online
Lecture period sommer term 2021: Wednesday, April 21th, 2021 - Friday, July 9th, 2021

 

al 2

Summary

Autonomous Learning research aims at understanding how autonomous systems can efficiently learn from the interaction with the environment, especially by having an integrated approach to decision making and learning, allowing systems to autonomously decide on actions, representations, hyper-parameters and model structures for the purpose of efficient learning. The term "autonomous" refers to the ability of the system to learn without or with only very limited external support, which includes manual intervention of humans, availability of pre-defined models or expert knowledge, and availability of large sets of sample data. Specific research topics are: Adaptation of the learning models / techniques based on observations, learning from interaction with the environment, re-using knowledge from one domain in another domain, detection of behaviour that deviates from 'usual' or expected behaviour, and learning from and with other systems of the same kind. The lecture gives an introduction to the field of autonomous learning with a particular focus on a utilisation of the different techniques within intelligent systems. Autonomous Learning is cutting edge research, which means that parts of the lecture are based on current research articles rather than on textbooks. Furthermore, a practitioner's perspective is combined with theoretical understanding of the concepts: the lecture units are combined with traditional exercises but also with practical tasks that have to be solved by making use of techniques discussed in the lecture.

 

Learning goals

The overall goal of the course is to derive a basic understanding of the motivation, the general concept, and particularly important methods covering the most prominent parts of the field of autonomous learning. This includes techniques for the following aspects of machine learning:

  • Fully autonomous learning behaviour: hyper-parameter optimisation, transfer learning, (self-)evaluation,
  • self-awareness or environment-awareness with a major focus on anomaly/novelty detection
  • By interaction with the environment via sensors and actuators: reinforcement learning
  • By efficiently integrating humans into the learning process: active learning
  • By interacting with other intelligent systems: collaborative learning
  • By using all the above: meta-learning


Particular goals are:

a) Knowledge/Skills:

Understanding of methods for achieving "intelligence" in technical systems, control of learning behaviour with minimal user interaction, continuous self-improvement of system behaviour, cooperation in learning between distributed technical systems

b) Abilities:

Selection and application of techniques of machine learning in technical systems under real-world conditions to control autonomous system behaviour

c) Competencies:

Ability to analyse autonomous learning processes and their behaviour, to determine and interpret relevant assessment parameters / Competence to plan, design and develop intelligent technical systems with the ability to learn autonomously

 

Basic literature

  • Thomas Mitchell: Machine Learning, The McGraw-Hill Companies, 1997, ISBN 978-0071154673
  • Ethem Alpaydin: Introduction to Machine Learning (Adaptive Computation and Machine Learning). The Mit Press, 3rd revised edition, 2014. ISBN: 978-0262028189
  • C. Müller-Schloer, S. Tomforde: Organic Computing - Technical Systems for Survival in the real World
  • B. Settles: Active Learning
  • M. Yamada, Jianhuii Chen, Yi Chang: Transfer Learning: Algorithms and Applications
  • C. Bishop: Pattern Recognition and Machine Learning (Information Science and Statistics)
  • Sutton, Richard S., and Andrew G. Barto. Introduction to reinforcement learning. Vol. 135. Cambridge: MIT press, 1998.
  • S. Russell and P. Norvig: Künstliche Intelligenz. Ein moderner Ansatz. 3. Aufl. PEARSON

 

Workload

30 h lecture, 30 h classroom exercise, 30 h practical exercise, 120 h self-study

Self-Organised Systems

birds

 

Bachelor seminar (infBSemIS-01a)

2 SWS, ECTS studiies, ECTS credits: 4
Language of instruction: german
Time and place: online
Lecture period summer term 2021: 19.4.2021 - 9.7.2021
For more Information UnivIS

 

Summary

The seminar is dedicated to the topic of "Self-organised Systems". In the context of this seminar, this is understood to mean sets of autonomous and technical units that work together to achieve a common goal. Different questions arise that have to be mastered.

The seminar in the winter semester 2020/21 is dedicated to the consistent, fast and reliable storage and the associated finding of content within such self-organized systems. This is examined using algorithms from peer-to-peer computing.

The seminar in summer term 2021 is dedicated to the cooperation of autonomous intelligent systems and the associated interaction patterns within such self-organized systems. This is examined using examples from autonomic and organic computing.

 

Learning goals

The students learn to independently acquire complex issues using the compact presentation, as is customary in scientific publications (i.e. papers, articles or specialist books) and to prepare them in an understandable form.

 

Workload

30 hours of participation in the seminar, 90 hours of self-study

Master Project Intelligent Systems

MP

 

Exercise  (infMPInS-01a)

4 SWS, ECTS-Credits: 10
Suitable for ERASMUS / exchange students, language of instruction: English
Time and place: by arrangement
Lecture period SS 2021: Thursday, April 22th, 2021 - Friday, July 9th, 2021
For more information UnivIS



Title: "Collaborative classification with Turtle Bots"


KickOff Meeting (online): Monday, April 12th at 2 pm
via https://uni-kiel.zoom.us/j/83011387731?pwd=LzgzTHNRV0tYOTM2Y3BmaUozVUtvdz09

Important: The team size is restricted - the KickOff Meeting is used to register participants


Description

There are two robots with different abilities. One robot can visually perceive objects, while the other robot can determine the weight and transport the object. Based on a collaborative feature determination, manually provided objects are to be correctly classified and sorted into appropriate containers. The learning technique for classification starts with no prior knowledge - it must independently and continuously evaluate its knowledge and specifically question the human user.

This requires the following steps and techniques:
- Setting up a laboratory environment incl. unloading mechanisms
- Individual feature determination of the individual robots
- Fusion of information and data representation
- Continuous training and evaluation of a classifier with Active Learning techniques
- Control of robot behaviour in ROS

Depending on the availability of hardware, the loading step can also be automated using a robot arm.

As a result of the task, the following artefacts are foreseen:
- Code base
- Short technical documentation
- Scientific description (IEEE Template, double Column, 8 pages)

The task requires that at least parts are done locally at the group's lab (i.e. robot-based tasks). Other parts can be done remotely. It will be subject to the team's discussion how this is organised.

For any questions, please contact Prof. Dr.-Ing. Sven Tomforde via e-mail: st@informatik.uni-kiel.de