Back Propogation Algorithm

Versione 1.0.0.0 (5,03 KB) da Anshuman Gupta

The code implements the Back prop algorithm for MLPs.

Segui

4.0

(2)

3,6K download

Aggiornato 2 apr 2009

Visualizza la licenza

The training input vectors and target vectors are read from files data1in and data1out respectively. The no of nodes in input and output layer is decided depending on the no. of rows in these datasets.
The no of hidden layers, No of nodes in each hidden layer and the target error (put 0.1) is to be input by the user.

Learning curve is plotted after every 100 epochs.
Learning factor can be varied using the slider at the bottom. This idea was picked from an algorithm created by by AliReza KashaniPour & Phil Brierley.
Activation function for hidden layers is logsig and linear for output layer!
Just press F5 and ve funn!
anshuman0387[at]yahoo[dot]com :)

Cita come

Anshuman Gupta (2026). Back Propogation Algorithm (https://it.mathworks.com/matlabcentral/fileexchange/23528-back-propogation-algorithm), MATLAB Central File Exchange. Recuperato marzo 18, 2026.

Compatibilità della release di MATLAB

Creato con R14SP1

Compatibile con qualsiasi release

Compatibilità della piattaforma

Windows macOS Linux

Categorie

AI and Statistics > Deep Learning Toolbox > Train Deep Neural Networks > Function Approximation, Clustering, and Control > Function Approximation and Clustering > Define Shallow Neural Network Architectures >

Scopri di più su Define Shallow Neural Network Architectures in Help Center e MATLAB Answers

Tag Aggiungi tag

Riconoscimenti

Ispirato da: Function Approximation Using Neural Network Without using Toolbox

Apri in una nuova scheda

Versione	Pubblicato	Note della release
1.0.0.0	2 apr 2009		Scarica