SluitenHelpPrint
Switch to English
Cursus: 201700080
201700080
Information Theory and Statistics 
Cursus informatie
Cursus201700080
Studiepunten (ECTS)5
CursustypeCursus
VoertaalEngels
ContactpersoonM.C. de Jongh
E-mailm.c.dejongh@utwente.nl
Docenten
Examinator
dr.ir. J. Goseling
Docent
M.C. de Jongh
Contactpersoon van de cursus
M.C. de Jongh
Collegejaar2022
Aanvangsblok
2A
AanmeldingsprocedureZelf aanmelden via OSIRIS Student
Inschrijven via OSIRISJa
Cursusdoelen
After passing the assessment of this course a student:
  1. knows Shannon entropy and mutual information, is able to perform computations involving these information measures and is able to estimate these measures from a data set,
  2. knows the Huffman, Lempel-Ziv and CTW data compression algorithms, and understands the limits on data compression,
  3. understands the connection between machine learning and data compression and is able to quantify performance limits on machine learning algorithms,
  4. is able to quantify the optimal performance that can be expected from a classification system in terms of information measures.
Inhoud
Information theory is a mathematical theory dealing with the fundamental principles of storing, processing, and transmitting data. The first half of this course covers the core concepts of information theory, including entropy and mutual information. These are then used to derive fundamental limits on data compression and communication. The second half of this course focuses on applications of information theory to statistics and machine learning. In particular, information theory will be used to develop performance limits on machine learning algorithms.

Assessment
1) Written exam (60 %, needs >= 5.5)
2) homework (20 %)
3) report, based on project or reading assignment (20 %)
Voorkennis
Basic probability theory, for instance from:
• B-AM M4,
• B-EE M8,
• B-CS/BIT M4 or
• 202001177 Probability Theory and Statistics (premaster M-CS).
Participating study
Master Computer Science
Participating study
Master Applied Mathematics
Participating study
Master Electrical Engineering
Verplicht materiaal
Handouts
Lecture notes
Aanbevolen materiaal
-
Werkvormen
Hoorcollege

Werkcollege

Toetsen
Test

SluitenHelpPrint
Switch to English