Linear Gradient Descent from lectures of Andrew Ng

version 1.0.0.0 (1.97 KB) by Lukas Tencer
This is an algorithm for fitting linear model to multivariate data.

887 Downloads

Updated 11 Feb 2013

View License

function [ args ] = geadientDescent( data )

where the lines of the matrix are datapoints and columns are dimensions, last dimension is one to be infered. It is implemented according to lectures of Andrew Ng.

You can set learning rate, normalization and stop criterion, edit the file.

default values are:

learning rate: 0.2
stop criterion: 0.0000001
normalization: yes

Also small dataset and script to load the dataset is present, also at the end of the file, there is commented out code to visualize 2D version of the algorithm.

If you wish to see the algorithm perform, do the following:

1. Unpack
2. x=loadData('2Dset')
3. gradientDescent(x)

enjoy!

It is free for any use. If you use it, please cite: http://ieeexplore.ieee.org/xpl/articleDetails.jsp?arnumber=6310525

Cite As

Lukas Tencer (2022). Linear Gradient Descent from lectures of Andrew Ng (https://www.mathworks.com/matlabcentral/fileexchange/40225-linear-gradient-descent-from-lectures-of-andrew-ng), MATLAB Central File Exchange. Retrieved .

MATLAB Release Compatibility
Created with R2012b
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!