Exercise:Self-Taught Learning

From Ufldl

Jump to: navigation, search
(Changed verification of data set)
Line 11: Line 11:
===Step One: Generate the input and test data sets===
===Step One: Generate the input and test data sets===
-
Download and decompress <tt>stl_exercise.zip</tt>, which contains starter code for this exercise. Additionally, you will need to download the datasets from the MNIST Handwritten Digit Database for this project. You will need to use the f
+
Download and decompress <tt>stl_exercise.zip</tt>, which contains starter code for this exercise. Additionally, you will need to download the datasets from the MNIST Handwritten Digit Database for this project.
-
To separate the the cases, you will need to fill in <tt>filterData.m</tt>, which should return a subset of the data set containing examples with labels within a certain bound. After implementing this function, run this step. The results of your function will be visualized as three rows, corresponding to the unlabelled training set, the labelled training set, and the test set. Ensure that the first row only contains digits 0 to 4, and the second and third only contains digits 5 to 9.
+
To separate the the cases, you will need to fill in <tt>filterData.m</tt>, which should return a subset of the data set containing examples with labels within a certain bound. After implementing this function, run this step. To test your function, the script will output the number of examples in the STL and the supervised training data set, which should be 30596 and 60000 respectively.
-
 
+
-
[[File:selfTaughtInput.png]]
+
===Step Two: Train the sparse autoencoder===
===Step Two: Train the sparse autoencoder===

Revision as of 19:47, 21 April 2011

Retrieved from "http://ufldl.stanford.edu/wiki/index.php/Exercise:Self-Taught_Learning"
Personal tools