Detalles del recurso
Pertenece a:
Caltech Authors
Descripción: 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.
Autor(es): 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
Contacto:
Localización:
* 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
