Exercise:Vectorization

From Ufldl

Jump to: navigation, search
Line 19: Line 19:
Now that you have vectorized the code, it is easy to learn larger sets of features on medium sized images. In this part of the exercise, you will use your sparse autoencoder to learn features for handwritten digits from the MNIST dataset.
Now that you have vectorized the code, it is easy to learn larger sets of features on medium sized images. In this part of the exercise, you will use your sparse autoencoder to learn features for handwritten digits from the MNIST dataset.
-
The MNIST data is available at [http://yann.lecun.com/exdb/mnist/]. Download the file <tt>train-images-idx3-ubyte.gz</tt> and decompress it. After obtaining the source images, we have [[Using the MNIST Dataset | provided functions ]] help you load them up as Matlab matrices.
+
The MNIST data is available at [http://yann.lecun.com/exdb/mnist/]. Download the file <tt>train-images-idx3-ubyte.gz</tt> and decompress it. After obtaining the source images, we have [[Using the MNIST Dataset | provided functions ]] help you load them up as Matlab matrices. While the provided functions allow you to load up both the labels and data, for this assignment, you will only need the data since the training is ''unsupervised''.
The following set of parameters worked well for us to learn good features on the MNIST dataset:
The following set of parameters worked well for us to learn good features on the MNIST dataset:

Revision as of 22:30, 28 April 2011

Personal tools