Mostra el registre d'ítem simple
Computational power of neural networks: a Kolmogorov complexity characterization
dc.contributor.author | Balcázar Navarro, José Luis |
dc.contributor.author | Gavaldà Mestre, Ricard |
dc.contributor.author | Siegelmann, H. |
dc.contributor.other | Universitat Politècnica de Catalunya. Departament de Ciències de la Computació |
dc.date.accessioned | 2016-01-27T12:29:39Z |
dc.date.available | 2016-01-27T12:29:39Z |
dc.date.issued | 1993-01-01 |
dc.identifier.citation | Balcázar Navarro, José Luis; Gavaldà Mestre, Ricard; Siegelmann, H. "Computational power of neural networks: a Kolmogorov complexity characterization". 1993. |
dc.identifier.uri | http://hdl.handle.net/2117/82120 |
dc.description.abstract | The computational power of neural networks depends on properties of the real numbers used as weights. We focus on networks restricted to compute in polynomial time, operating on boolean inputs. Previous work has demonstrated that their computational power happens to coincide with the complexity classes P and P/poly, respectively, for networks with rational and arbitrary real weights. Here we prove that the crucial concept that characterizes this computational power is the Kolmogorov complexity of the weights, in the sense that, for each bound on this complexity, the networks can solve exactly the problems in a related nonuniform complexity class located between P and P/poly. By proving that the family of such nonuniform classes is infinite, we show that neural networks can be classified into an infinite hierarchy of different computing capabilities. |
dc.format.extent | 27 p. |
dc.language.iso | eng |
dc.relation.ispartofseries | LSI-93-43-R |
dc.subject | Àrees temàtiques de la UPC::Informàtica |
dc.subject.other | Neural networks |
dc.subject.other | Turing Machines |
dc.subject.other | Kolmogorov complexity |
dc.title | Computational power of neural networks: a Kolmogorov complexity characterization |
dc.type | External research report |
dc.rights.access | Open Access |
dc.description.version | Postprint (published version) |
local.personalitzacitacio | true |
Fitxers d'aquest items
Aquest ítem apareix a les col·leccions següents
-
Reports de recerca [1.107]