DOIONLINE

DOIONLINE NO - IJACEN-IRAJ-DOIONLINE-9201

Publish In
International Journal of Advance Computational Engineering and Networking (IJACEN)-IJACEN
Journal Home
Volume Issue
Issue
Volume-5,Issue-9  ( Sep, 2017 )
Paper Title
Neural Network Application for Prediction
Author Name
Elda Xhumari
Affilition
Department of Informatics, Faculty of Natural Sciences, University of Tirana
Pages
79-81
Abstract
Neural networks are one of the areas of research in the field of artificial intelligence, based on attempts to reproduce the human neural system. The ability of the neural system to learn and correct mistakes, which should allow simulating, albeit roughly enough, the work of the human brain [1]. The most important feature of the network, which attests to its wide capabilities and huge potential, is the parallel processing of information, which speeds up the information processing. In addition, with a large number of interneuronal connections, the network acquires resistance to errors that occur on certain lines. Nowadays, neural networks are used to solve a big number of problems, one of which is the prediction problem. Keywords: Neural networks, prediction, training, NN architecture, NN types, activation function
  View Paper