image thumbnail

Grid Search Function for Neural Networks

version 1.0.0.0 (2.4 KB) by caghangir
Grid Search Function for Neural Networks

362 Downloads

Updated 26 May 2017

View License

I created this function for my projects to find best hyper-parameters of Neural Networks.
It takes 5 different hyper-parameters such as;
- hidden node size of layer 1
- hidden node size of layer 2
- optimizer type
- maximum epoch
- transfer function
There is an example code block top of the function. You just add which hyper-parameters you want to try. Function will try 10-fold cross validation of each combination that is created using your hyper-parameters. Finally, find best hyper-parameter combination and return these as cell. You can use the cell directly as parameters of your Neural Network.
You need to give train with label, function automatically create %90 train %10 validation dataset.
New version is coming with more features.

Cite As

caghangir (2021). Grid Search Function for Neural Networks (https://www.mathworks.com/matlabcentral/fileexchange/63132-grid-search-function-for-neural-networks), MATLAB Central File Exchange. Retrieved .

MATLAB Release Compatibility
Created with R2016a
Compatible with any release
Platform Compatibility
Windows macOS Linux

Community Treasure Hunt

Find the treasures in MATLAB Central and discover how the community can help you!

Start Hunting!