Exercise:Self-Taught Learning
From Ufldl
| Line 8: | Line 8: | ||
To demonstrate the effectiveness of this method, we will train the sparse autoencoder on an unlabeled data set comprised out of all the digits 0 to 9, and then test them on the digits 5 to 9. The purpose of this is to demonstrate that self-taught learning can be surprisingly effective in improving results even if some data set items do not fall within the classes of our classification task. | To demonstrate the effectiveness of this method, we will train the sparse autoencoder on an unlabeled data set comprised out of all the digits 0 to 9, and then test them on the digits 5 to 9. The purpose of this is to demonstrate that self-taught learning can be surprisingly effective in improving results even if some data set items do not fall within the classes of our classification task. | ||
| + | |||
| + | === Support Code/Data === | ||
| + | |||
| + | The following additional files are required for this exercise: | ||
| + | * [http://yann.lecun.com/exdb/mnist/train-images-idx3-ubyte.gz MNIST Dataset (Training Images)] | ||
| + | * [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 ]] | ||
| + | This exercise has dependencies on the previous exercises: | ||
| + | * [[Exercise:Sparse Autoencoder]] | ||
| + | * [[Exercise:Vectorization]] | ||
| + | * [[Exercise:Softmax Regression]] | ||
===Step One: Generate the input and test data sets=== | ===Step One: Generate the input and test data sets=== | ||
