Dependence of Computational Models on Input Dimension: Tractability of Approximation and Optimization Tasks

0368521 - ÚI 2012 RIV US eng J - Journal Article
Kainen, P.C. - Kůrková, Věra - Sanguineti, M.
Dependence of Computational Models on Input Dimension: Tractability of Approximation and Optimization Tasks.
IEEE Transactions on Information Theory. Roč. 58, č. 2 (2012), s. 1203-1214. ISSN 0018-9448. E-ISSN 1557-9654
R&D Projects: GA MŠMT(CZ) ME10023; GA ČR GA201/08/1744; GA ČR GAP202/11/1368
Grant - others:CNR-AV ČR(CZ-IT) Project 2010–2012 Complexity of Neural-Network and Kernel Computational Models
Institutional research plan: CEZ:AV0Z10300504
Keywords : dictionary-based computational models * high-dimensional approximation and optimization * model complexity * polynomial upper bounds
Subject RIV: IN - Informatics, Computer Science
Impact factor: 2.621, year: 2012

The role of input dimension is studied in approximating, in various norms, target sets of d-variable functions using linear combinations of adjustable computational units. Results are applied to approximation and solution of optimization problems by neural networks with perceptron and Gaussian radial computational units.
Permanent Link: http://hdl.handle.net/11104/0202846