The attached zip file contains what is needed to implement a two layer neural network. This will hopefully be the first part of a broader collection of neural network tools.
It can be used to train and simulate a NN with two layers, an input layer and an output layer. The output layer's activation function can be the simple perceptron rule, or the logistic sigmoid function.
The perceptron rules work fine, however the logistic sigmoid function seems to be off. If anyone wishes to help with debugging I would be grateful. The code doesn't do any error checking for inputs, but the enclosed PDF file give examples of usage. As time progresses and I figure out whats going on with the logistic sigmoid function I will be updating these files with more online help.
Cite As
Timothy Felty (2024). Simple Neural Network (https://www.mathworks.com/matlabcentral/fileexchange/9262-simple-neural-network), MATLAB Central File Exchange. Retrieved .
MATLAB Release Compatibility
Platform Compatibility
Windows macOS LinuxCategories
- AI and Statistics > Deep Learning Toolbox > Function Approximation, Clustering, and Control > Function Approximation and Clustering > Define Shallow Neural Network Architectures >
Tags
Community Treasure Hunt
Find the treasures in MATLAB Central and discover how the community can help you!
Start Hunting!Discover Live Editor
Create scripts with code, output, and formatted text in a single executable document.
Version | Published | Release Notes | |
---|---|---|---|
1.0.0.0 |