Number of the records: 1
Probabilistic Lower Bounds for Approximation by Shallow Perceptron Networks
- 1.0473964 - ÚI 2018 RIV GB eng J - Journal Article
Kůrková, Věra - Sanguineti, M.
Probabilistic Lower Bounds for Approximation by Shallow Perceptron Networks.
Neural Networks. Roč. 91, July (2017), s. 34-41. ISSN 0893-6080. E-ISSN 1879-2782
R&D Projects: GA ČR GA15-18108S
Institutional support: RVO:67985807
Keywords : shallow networks * perceptrons * model complexity * lower bounds on approximation rates * Chernoff-Hoeffding bounds
OECD category: Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8)
Impact factor: 7.197, year: 2017
Limitations of approximation capabilities of shallow perceptron networks are investigated. Lower bounds on approximation errors are derived for binary-valued functions on finite domains. It is proven that unless the number of network units is sufficiently large (larger than any polynomial of the logarithm of the size of the domain) a good approximation cannot be achieved for almost any uniformly randomly chosen function on a given domain. The results are obtained by combining probabilistic Chernoff-Hoeffing bounds with estimates of the sizes of sets of functions exactly computable by shallow networks with increasing numbers of units.
Permanent Link: http://hdl.handle.net/11104/0271067
File Download Size Commentary Version Access a0473964.pdf 16 549.9 KB Publisher’s postprint require
Number of the records: 1