-> This is a solution to the Self Taught Learning exercise in the Stanford UFLDL Tutorial(http://ufldl.stanford.edu/wiki/index.php/Exercise:Self-Taught_Learning) -> 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 gunzip data files and the code file 'selfTaughtLearning.py' -> Put them in the same folder, extract the gunzips and run the program by typing in 'python selfTaughtLearning.py' in the command line -> You should first get an image of the learned Autoencoder weights similar to 'output.png' -> You should get an output saying 'Accuracy : 0.982', which signifies an accuracy of 98.2% -> The code takes about 330 minutes to execute on an i3 processor, yes that's right! Code written by: Siddharth Agrawal Email ID: siddharth.950@gmail.com