Learning Automata

Course Description

Fundamentals and definitions of machine learning. State and action probabilities, and standard patterns of machine learning behaviour. Mathematical models of neuron and neural networks, diversity and properties of learning alorithms. Claster analisys, knowledge representation, compression and representation from uncomplete data. Basics of associative memories. Recursive networks and processing of time dependent patterns. Learning algorithms: Back-propagation with extensions, Kohonen and Cascade correlation algorithm, Convolutional networks, Deep learning, WTA (Winner-Takes-All). Feature extraction by competitive learning - interactive or on-line learning, Sarsa and Q-learning algorithm, Markov models. Intelligent agents and selfadaptive control of communication services.

Learning Outcomes

  1. to define concept, methods and architectures typical for machine learnings
  2. to explain how machine learning operate and basic purpose
  3. to apply knowledge about machine learning to communication services
  4. to analyze functions of machine learned components, as well as their interactions in order to find appropriate solution
  5. to analyze organization and results produced by machine learning modela
  6. to create machine learned models including various types of recognition and self-adaptation
  7. to evaluate and assess solutions based on different methods of machine learning

Forms of Teaching

Lectures

Independent assignments

Laboratory

Grading Method

Continuous Assessment Exam
Type Threshold Percent of Grade Threshold Percent of Grade
Laboratory Exercises 0 % 20 % 0 % 0 %
Homeworks 0 % 10 % 0 % 0 %
Class participation 0 % 10 % 0 % 0 %
2. Mid Term Exam: Written 0 % 20 % 0 %
Final Exam: Written 0 % 20 %
Final Exam: Oral 20 %
Exam: Written 40 % 0 %
Exam: Oral 30 %

Week by Week Schedule

  1. Perceptron (learning paradigms,Hebbian learning, competitive learning, Boltzmann learning)
  2. Multilayer perceptron (error-backpropagation learning, credit-assignment problem, backpropagation through time)
  3. Multilayer perceptron (error-backpropagation learning, credit-assignment problem, backpropagation through time)
  4. Radial basis function networks (solving interpolation problem with radial basis function networks, generalized radial basis function networks, relation to regularization theory)
  5. Self-organizing networks (Hebbian non-supervised learning, Oja's learning rule, PCA using self-organizing network, Sanger's learning rule, Competitive non-supervised learning, winner-takes-all network, Kohonen's self-organizing maps)
  6. Recurrent neural networks (Hopfield network, Hopfield network energy function, Boltzman machine, Elman networks, Jordan networks) and learning algorithms (back propagation through time, reccurent backpropagation)
  7. Online learning
  8. Midterm exam
  9. Online learning
  10. Deep convolutional networks: layers, architectures, visualization, fine tuning, applications, implementation
  11. Deep convolutional networks: layers, architectures, visualization, fine tuning, applications, implementation
  12. Decision trees (ID3, C4;5)
  13. K-means algorithm
  14. K-medoids algorithm, Max-min clustering
  15. Final exam

Study Programmes

University graduate
[FER3-HR] Audio Technologies and Electroacoustics - profile
Elective Courses (1. semester) (3. semester)
[FER3-HR] Communication and Space Technologies - profile
Elective Courses (1. semester) (3. semester)
[FER3-HR] Computational Modelling in Engineering - profile
Elective Courses (1. semester) (3. semester)
[FER3-HR] Computer Engineering - profile
Elective Courses (1. semester) (3. semester)
[FER3-HR] Computer Science - profile
Elective Courses (1. semester) (3. semester)
[FER3-HR] Control Systems and Robotics - profile
Elective Courses (1. semester) (3. semester)
[FER3-HR] Data Science - profile
Elective Courses (1. semester) (3. semester)
[FER3-HR] Electrical Power Engineering - profile
Elective Courses (1. semester) (3. semester)
[FER3-HR] Electric Machines, Drives and Automation - profile
Elective Courses (1. semester) (3. semester)
[FER3-HR] Electronic and Computer Engineering - profile
Elective Courses (1. semester) (3. semester)
[FER3-HR] Electronics - profile
Elective Courses (1. semester) (3. semester)
[FER3-HR] Information and Communication Engineering - profile
Elective Courses (1. semester) (3. semester)
[FER3-HR] Network Science - profile
Elective Courses (1. semester) (3. semester)
Elective Courses of the Profile (1. semester) (3. semester)
[FER3-HR] Software Engineering and Information Systems - profile
Elective Courses (1. semester) (3. semester)
[FER2-HR] Telecommunication and Informatics - profile
Specialization Course (1. semester) (3. semester)

Literature

(.), Neural Networks and Learning Machines, Simon Haykin, Prentice Hall, c2009, New York,
(.), Parallel Distributed Processing: Explorations in the Microstructure of Cognition David E. Rumelhart MIT Press 1987.,
(.), Reinforcement Learning:An Introduction Richard S. Sutton, Andrew G. Barto MIT Press, Cambridge 1998.,

For students

General

ID 222473
  Winter semester
5 ECTS
L1 English Level
L1 e-Learning
30 Lectures
0 Seminar
0 Exercises
15 Laboratory exercises
0 Project laboratory

Grading System

85 Excellent
70 Very Good
60 Good
50 Sufficient