Exercise:Softmax Regression

From Ufldl

Jump to: navigation, search
(Step 2: Implement softmaxCost)
(Support Code/Data)
Line 7: Line 7:
You will need to modify '''<tt>softmaxCost.m</tt>''' and '''<tt>softmaxPredict.m</tt>''' for this exercise.
You will need to modify '''<tt>softmaxCost.m</tt>''' and '''<tt>softmaxPredict.m</tt>''' for this exercise.
-
=== Support Code/Data ===
+
=== Dependencies ===
The following additional files are required for this exercise:
The following additional files are required for this exercise:
Line 13: Line 13:
* [http://yann.lecun.com/exdb/mnist/train-labels-idx1-ubyte.gz MNIST Dataset (Training Labels)]
* [http://yann.lecun.com/exdb/mnist/train-labels-idx1-ubyte.gz MNIST Dataset (Training Labels)]
* [[Using the MNIST Dataset | Support functions for loading MNIST in Matlab ]]
* [[Using the MNIST Dataset | Support functions for loading MNIST in Matlab ]]
 +
 +
You will also need:
 +
* computeNumericalGradient.m from [[Exercise:Sparse Autoencoder]]
 +
 +
''If you have not completed the exercises listed above, we strongly suggest you complete them first.''
=== Step 0: Initialize constants and parameters ===
=== Step 0: Initialize constants and parameters ===

Revision as of 02:37, 7 May 2011

Personal tools