Počet záznamů: 1
Constructive Lower Bounds on Model Complexity of Shallow Perceptron Networks
- 1.0474092 - ÚI 2019 RIV US eng J - Článek v odborném periodiku
Kůrková, Věra
Constructive Lower Bounds on Model Complexity of Shallow Perceptron Networks.
Neural Computing & Applications. Roč. 29, č. 7 (2018), s. 305-315. ISSN 0941-0643. E-ISSN 1433-3058
Grant CEP: GA ČR GA15-18108S
Institucionální podpora: RVO:67985807
Klíčová slova: shallow and deep networks * model complexity and sparsity * signum perceptron networks * finite mappings * variational norms * Hadamard matrices
Obor OECD: Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8)
Impakt faktor: 4.664, rok: 2018
Limitations of shallow (one-hidden-layer) perceptron networks are investigated with respect to computing multivariable functions on finite domains. Lower bounds are derived on growth of the number of network units or sizes of output weights in terms of variations of functions to be computed. A concrete construction is presented with a class of functions which cannot be computed by signum or Heaviside perceptron networks with considerably smaller numbers of units and smaller output weights than the sizes of the function’s domains. A subclass of these functions is described whose elements can be computed by two-hidden-layer perceptron networks with the number of units depending on logarithm of the size of the domain linearly.
Trvalý link: http://hdl.handle.net/11104/0271209
Název souboru Staženo Velikost Komentář Verze Přístup a0474092.pdf 8 495.8 KB Vydavatelský postprint vyžádat
Počet záznamů: 1