1) La descarga del recurso depende de la página de origen
2) Para poder descargar el recurso, es necesario ser usuario registrado en Universia

Opción 1: Descargar recurso

Opción 2: Descargar recurso

Detalles del recurso


A neuron is modeled as a linear threshold gate, and the network architecture considered is the layered feedforward network. It is shown how common arithmetic functions such as multiplication and sorting can be efficiently computed in a shallow neural network. Some known results are improved by showing that the product of two n-bit numbers and sorting of n n-bit numbers can be computed by a polynomial-size neural network using only four and five unit delays, respectively. Moreover, the weights of each threshold element in the neural networks require O(log n)-bit (instead of n -bit) accuracy. These results can be extended to more complicated functions such as multiple products, division, rational functions, and approximation of analytic functions.

Pertenece a

Caltech Authors  


Siu, Kai -  Yeung -  Bruck, Jehoshua - 

Id.: 55239732

Versión: 1.0

Estado: Final

Tipo:  application/pdf -  image/png - 

Tipo de recurso: Article  -  PeerReviewed  - 

Tipo de Interactividad: Expositivo

Nivel de Interactividad: muy bajo

Audiencia: Estudiante  -  Profesor  -  Autor  - 

Estructura: Atomic

Coste: no

Copyright: sí

Formatos:  application/pdf -  image/png - 

Requerimientos técnicos:  Browser: Any - 

Relación: [References] http://resolver.caltech.edu/CaltechAUTHORS:20120503-090033553
[References] http://authors.library.caltech.edu/31288/

Fecha de contribución: 27-dic-2012


* Siu, Kai-Yeung and Bruck, Jehoshua (1990) Neural computation of arithmetic functions. Proceedings of the IEEE, 78 (10). pp. 1669-1675. ISSN 0018-9219 http://resolver.caltech.edu/CaltechAUTHORS:20120503-090033553

Otros recursos del mismo autor(es)

  1. Discordance between morphological and taxonomic diversity: land snails of oceanic archipelagos International audience
  2. Data movement in flash memories NAND flash memories are the most widely used non-volatile memories, and data movement is common in f...
  3. Universal rewriting in constrained memories A constrained memory is a storage device whose elements change their states under some constraints. ...
  4. Automatic quantification of the myocardial extracellular volume by cardiac computed tomography: Synthetic ECV by CCT. BACKGROUND: The quantification of extracellular volume fraction (ECV) by Cardiac Computed Tomography...
  5. Switch Codes: Codes for Fully Parallel Reconstruction Network switches and routers scale in rate by distributing the packet read/write operations across m...

Otros recursos de la mismacolección

  1. Reducing repair traffic for erasure coding-based storage via interference alignment We consider the problem of recovering from a single node failure in a storage system based on an (n,...
  2. Leukocyte count and two-part differential in whole blood based on a portable microflow cytometer This work demonstrated leukocyte count and two-part leukocyte differential from the whole blood base...
  3. On combining information-theoretic and cryptographic approaches to network coding security against the pollution attack In this paper we consider the pollution attack in network coded systems where network nodes are comp...
  4. Multiple target detection using Bayesian learning n this paper, we study multiple target detection using Bayesian learning. The main aim of the paper ...
  5. Unidirectional vertical emission from photonic crystal nanolasers Here, we emphasize the importance of using a bottom reflector to achieve unidirectional vertical emi...

Aviso de cookies: Usamos cookies propias y de terceros para mejorar nuestros servicios, para análisis estadístico y para mostrarle publicidad. Si continua navegando consideramos que acepta su uso en los términos establecidos en la Política de cookies.