Exercise:Softmax Regression

From Ufldl

Jump to: navigation, search
m (Changed "output matrix" to "ground truth matrix")
m (Removed 'cross validation')
Line 99: Line 99:
Factoring <tt>softmaxTrain</tt> out as a function means that you will be able to easily reuse it to train softmax models on other data sets in the future by invoking the function with different parameters.
Factoring <tt>softmaxTrain</tt> out as a function means that you will be able to easily reuse it to train softmax models on other data sets in the future by invoking the function with different parameters.
-
=== Step 5: Cross-validation ===
+
=== Step 5: Testing ===
Now that you've trained your model, you will cross-validate it against the MNIST test set, comprising 10000 28x28 images. Code has been provided to compute the accuracy (the proportion of correctly classified images) of your model. Our implementation achieved an accuracy of 92%. If your model's accuracy is significantly less (less than 91%), check your code, ensure that you are using the trained weights, and that you are training your model on the full 60000 training images. Conversely, if your accuracy is too high (99-100%), ensure that you have not accidentally trained your model on the test set as well.
Now that you've trained your model, you will cross-validate it against the MNIST test set, comprising 10000 28x28 images. Code has been provided to compute the accuracy (the proportion of correctly classified images) of your model. Our implementation achieved an accuracy of 92%. If your model's accuracy is significantly less (less than 91%), check your code, ensure that you are using the trained weights, and that you are training your model on the full 60000 training images. Conversely, if your accuracy is too high (99-100%), ensure that you have not accidentally trained your model on the test set as well.
[[Category:Exercises]] [[Category:TODO]]
[[Category:Exercises]] [[Category:TODO]]

Revision as of 02:10, 29 April 2011

Personal tools