Asian Science Citation Index is committed to provide an authoritative, trusted and significant information by the coverage of the most important and influential journals to meet the needs of the global scientific community.  
ASCI Database
308-Lasani Town,
Sargodha Road,
Faisalabad, Pakistan
Fax: +92-41-8815544
Contact Via Web
Suggest a Journal
Journal of Engineering and Applied Sciences
Year: 2007  |  Volume: 2  |  Issue: 12  |  Page No.: 1791 - 1794

Modeling of Technical Objects’ Refusal with the Help of Neural Networks

Khalil Yaghi    

Abstract: In this research, the refusal of technical objects in mass production uses Neural Network as a model. A neural network is a collection of interconnected elements or units. However, the phrase neural network means an amazing variety of things to a remarkable diversity of researchers. For biologists it refers to a mass of gray matter or, perhaps, a biologically faithful model of some part of the brain. For psychologists and other cognitive scientists, `neural` (or `connectionist`) network denotes a virtual machine architecture that has come to be seriously considered as a model of the mind. To a theoretical computer scientist, `neural network` is likely to mean a network of threshold logic gates. But to some computer scientists, a neural network is a Markov process, evolving through time in a stochastic search for globally optimal states. And to still others, a neural network is a collection of analog devices, continuously evolving in time under the direction of certain differential equations. To a physicist, a neural network may be a dynamical system evolving in time toward attractors of various types, or it might be a low-level substrate over which large-scale average behavior can be studied in the manner of statistical mechanics. To a functional analyst, a neural network is likely to be a particular kind of function approximator. To statisticians of various sorts, neural network learning is a realization of a scheme for estimating parameters and selecting among different models using Bayesian or information-theoretic or maximum-likelihood methods.

Fulltext    |   Related Articles   |   Back
  Related Articles

Copyright   |   Desclaimer   |    Privacy Policy   |   Browsers   |   Accessibility