Number of the records: 1
Limitations of Shallow Networks Representing Finite Mappings
- 1.
SYSNO ASEP 0485613 Document Type J - Journal Article R&D Document Type Journal Article Subsidiary J Článek ve WOS Title Limitations of Shallow Networks Representing Finite Mappings Author(s) Kůrková, Věra (UIVT-O) RID, SAI, ORCID Source Title Neural Computing & Applications. - : Springer - ISSN 0941-0643
Roč. 31, č. 6 (2019), s. 1783-1792Number of pages 10 s. Language eng - English Country US - United States Keywords shallow and deep networks ; sparsity ; variational norms ; functions on large finite domains ; finite dictionaries of computational units ; pseudo-noise sequences ; perceptron networks Subject RIV IN - Informatics, Computer Science OECD category Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8) R&D Projects GA15-18108S GA ČR - Czech Science Foundation (CSF) GA18-23827S GA ČR - Czech Science Foundation (CSF) Method of publishing Open access Institutional support UIVT-O - RVO:67985807 UT WOS 000470746700008 EID SCOPUS 85052492938 DOI 10.1007/s00521-018-3680-1 Annotation Limitations of capabilities of shallow networks to efficiently compute real-valued functions on finite domains are investigated. Efficiency is studied in terms of network sparsity and its approximate measures. It is shown that when a dictionary of computational units is not sufficiently large, computation of almost any uniformly randomly chosen function either represents a well-conditioned task performed by a large network or an ill-conditioned task performed by a network of a moderate size. The probabilistic results are complemented by a concrete example of a class of functions which cannot be efficiently computed by shallow perceptron networks. The class is constructed using pseudo-noise sequences which have many features of random sequences but can be generated using special polynomials. Connections to the No Free Lunch Theorem and the central paradox of coding theory are discussed. Workplace Institute of Computer Science Contact Tereza Šírová, sirova@cs.cas.cz, Tel.: 266 053 800 Year of Publishing 2020 Electronic address http://dx.doi.org/10.1007/s00521-018-3680-1
Number of the records: 1