Subjects

Your browser does not support JavaScript, or its support is disabled. Some features may not be available.

Theoretical Issues in Neural Networks - Approximation - NAIL026

Title:	Teoretické otázky neuronových sítí - aproximace
Form of teaching:	lecture
Guaranteed by:	Department of Theoretical Computer Science and Mathematical Logic (32-KTIML)
Faculty:	Faculty of Mathematics and Physics
Actual:	from 2022
Duration in semesters:	1
Semester:	winter
E-Credits:	3
Hours per week, examination:	winter s.:2/0, Ex [HT]
Capacity:	unlimited
Maximum number of enrolled students:	unlimited
Min. number of students:	unlimited
4EU+:	no
Virtual mobility / capacity:	no
State of the course:	cancelled
Language:	Czech
Teaching methods:	full-time
Repeated enrollment:	2 / 2 / 2 / 2

Guarantor:	Mgr. Roman Neruda, CSc.
Class:	Informatika Mgr. - volitelný
Classification:	Informatics > Theoretical Computer Science
Pre-requisite :	NAIL002

Opinion survey results Schedule Noticeboard

Annotation -

The universal approximation property will be studied for different architectures of neural networks (multilayer perceptron, RBF networks, Gaussian bars). Functional equivalence and similar properties will be studied with consequences for genetic learning of neural networks.

Last update: G_I (31.10.2001)

Aim of the course - Czech

Na přednášce bude vyšetřována vlastnost univerzální aproximace na různých

architekturách NS

Last update: T_KTI (26.05.2008)

Literature - Czech

Šíma, J, Neruda R: Teoretické otázky neuronových sítí, Matfyzpress, 1997.

Last update: Neruda Roman, Mgr., CSc. (02.05.2006)

Syllabus -

The universal approximation property will be studied for different

architectures of neural networks (multilayer perceptron, RBF networks,

Gaussian bars). Functional equivalence and similar properties will be

studied with consequences for genetic learning of neural networks.

Last update: G_I (17.05.2004)