Course detail

Machine Learning

FEKT-MSTUAcad. year: 2012/2013

The field of machine learning is concerned with the question of how
to construct computer programs that automatically improve with
experience. The goal of the subject is to present the key algorithms
and theory that form the core of machine learning. Machine learning
is interdisciplinary, draws on concepts and results from many
fields, including statistics, artificial intelligence, information
theory, philosophy, biology, cognitive science, and control theory.

Language of instruction

Czech

Number of ECTS credits

5

Mode of study

Not applicable.

Guarantor

Ing. Petr Honzík, Ph.D.

Department

Department of Control and Instrumentation (UAMT)

Learning outcomes of the course unit

Students obtain knowledge about the key methods of machine learning.

Prerequisites

The subject knowledge on the Bachelor´s degree level is requested.

Co-requisites

Not applicable.

Planned learning activities and teaching methods

Teaching methods depend on the type of course unit as specified in the article 7 of BUT Rules for Studies and Examinations.

Assesment methods and criteria linked to learning outcomes

Project - 20 points
Examination - 80 points

Course curriculum

1. Machine learning paradigms. Terminology. Concept learning. Basics of information theory.
2. Statistics in machine learning.
3. Instance based learning.
4. Decision trees.
5. Model performance estimation.
6. Loss functions. Preprocessing.
7. Genetic algorithms. Ant colony optimization.
8. Bayesian learning.
9. Linear regression. Discriminant analysis. Support vector machine.
10. Data mining.
11. Meta learning.
12. Unsupervised learning.

Work placements

Not applicable.

Aims

The goal of the subject is to present the key algorithms and theory that form the core of machine learning.

Specification of controlled education, way of implementation and compensation for absences

The content and forms of instruction in the evaluated course are specified by a regulation issued by the lecturer responsible for the course and updated for every academic year.

Recommended optional programme components

Not applicable.

Prerequisites and corequisites

Not applicable.

Basic literature

Honzík P.: Strojové učení. Elektonická skripta VUT. (CS)

Recommended reading

Mitchell, Tom M. Machine learning. Boston : McGraw-Hill, 1997. 414 s. McGraw-Hill series in computer science. ISBN 0-07-042807-7. (EN)

Classification of course in study plans

  • Programme EEKR-M Master's

    branch M-KAM , 2 year of study, winter semester, elective specialised

  • Programme EEKR-M Master's

    branch M-KAM , 2 year of study, winter semester, elective specialised

  • Programme EEKR-CZV lifelong learning

    branch EE-FLE , 1 year of study, winter semester, elective specialised

Type of course unit

 

Lecture

26 hod., optionally

Teacher / Lecturer

Ing. Petr Honzík, Ph.D.

Syllabus

Machine learning as the integration of artificial intelligence and cognive sciences. Computational processes that are related to learning. Selection of learning algorithms.
Training and testing data. Solution space. Learning and searching.
Natural and human learning. Problem representation language. Learning algorithms with numerical and symbolic inputs.
Methods of decision-tree induction. Presence of noise, incomplete description of examples.
Tree-to-rules transformation, generation of rules.
Perceptrons. Logical neural networks.
Kohonen maps.
Genetic algorithms, genetic programming. Comparision with biological systems.
Pattern recognition. Generalization. Nearest-neghbor method (k-NN).
Instance-based learning (IBL algorithms).
Bayesian classifiers.
Reinforcement learning.
Description and demonstration of applications.

Exercise in computer lab

26 hod., compulsory

Teacher / Lecturer

Ing. Petr Honzík, Ph.D.

Syllabus

Introduction, safety training.
Introduction to decision trees and program See5 for decision trees induction.
Practical training on program See5.
Introduction to genetic algorithms. GA toolbox for Matlab.
Practical use of GA.
Introduction to IBL methods for text recognition.
Work on individual projects.
Individual work.
Individual work.
Commitment of individual work.
Presentation of individual work.
Evaluation.