-> This is a solution to the Sparse Autoencoder exercise in the Stanford UFLDL Tutorial(http://ufldl.stanford.edu/wiki/index.php/Exercise:Sparse_Autoencoder)
-> The code has been written in Python using Scipy, Numpy and Matplotlib
-> The code is bound by The MIT License (MIT)

Running the code:

-> Download the data file 'IMAGES.mat' and the code file 'sparseAutoencoder.py'
-> Put them in the same folder, and run the program by typing in 'python sparseAutoencoder.py' in the command line
-> You should get an output similar to the file 'output.png'
-> The code takes about one and a half minutes to execute on an i3 processor