ID2225 Learning Machines 7.5 credits

Lärande maskiner

Please note

The information on this page is based on a course syllabus that is not yet valid.

  • Education cycle

    Second cycle
  • Main field of study

    Computer Science and Engineering
  • Grading scale

    A, B, C, D, E, FX, F

Course offerings

Autumn 18 for programme students

Autumn 19 for programme students

Intended learning outcomes

1. Independent problem-solving

  • Take part of the literature about learning machines and understand their role both historical and today and in the future.
  • Base own understanding around learning machines in existing solutions to evaluate the efficiency in the own solutions.
  • Analyse statistical confounders, overfitting as well as generalizability in own solutions based on learning machines.
  • Carry out self critical review of own programming of learning machines including ethical perspectives and sustainability perspectives, as well as to document the same.

2. Master abstraction

  • Define what a learning machine are and is not.
  • Identify relevant concepts and applicable methods and tools.
  • Master the meta level through modelling of different solutions based on learning machines that is to be able to talk about these using adequate terminology.
  • Associate critically different relevant concepts and phenomena with learning machines.
  • Instrumentalize relevant abstract concepts.

3. Implement learning machines

  • Use tools to build own learning machines, as well as analyse others'.
  • Program, test and evaluate critically own software for learning machines.
  • Estimate the correctness and the computational complexity in programme for learning machines.

Course main content

  • AI basis for learning machines.
  • Statistical learning theory I: Perceptrons and neural networks.
  • Statistical learning theory II: The learning problem.
  • Machine learning methods.
  • Internet psychiatry as a typical case for learning machines.
  • Critical perspectives on learning machines.
  • Systematic properties of learning machines LM2LM communication and learning in multi agent systems.
  • Technological change and learning the future of machines.
  • Applications of learning machines.

Disposition

The basis consists of a lectures that covers established literature. Invited lectures cover deep technical fields and applications. New platforms for interactive software that supports development of learning machines come be used.

Eligibility

Admitted to a master's programme at KTH in the main field of study.

Literature

Course compendium and open Internet resources.

Examination

  • RAP1 - Examination report, 4.5, grading scale: A, B, C, D, E, FX, F
  • SEM1 - Active participiation in seminars, 3.0, grading scale: P, F

Offered by

EECS/Computational Science and Technology

Examiner

Magnus Boman <mab@kth.se>

Version

Course syllabus valid from: Spring 2019.
Examination information valid from: Spring 2019.