Automated System for Constructing a Neural Network by Back Propagation Error

Volume 21 No 2 (2023)

Khalid Altarawneh

DOI: 10.48047/NQ.2023.21.2.NQ23065

Abstract

For improving the construction of neural networks, the back propagation method used to increase the intelligence of advanced machines. Stereotypical input data is considered in this paper since we deal with multilayer feed forward network. The backpropagation method is used to not only connect each neuron in each layer to all neuron in the next layer, but also adjust weights between neurons. In this paper, the direct calculation of results by a trained network is very fast even training the network can be a rather lengthy process

Keywords

Neural Network, Back Propagation Error, Feed forward Neural Network, single layer Neural Network and multi layers Neural Network.

Copyright © Neuroquantology

Creative Commons License
This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.

Articles published in the Neuroquantology are available under Creative Commons Attribution Non-Commercial No Derivatives Licence (CC BY-NC-ND 4.0). Authors retain copyright in their work and grant IJECSE right of first publication under CC BY-NC-ND 4.0. Users have the right to read, download, copy, distribute, print, search, or link to the full texts of articles in this journal, and to use them for any other lawful purpose.