Exercise:Vectorization
From Ufldl
(→MNIST) |
|||
Line 9: | Line 9: | ||
Use the following parameters for the MNIST dataset: | Use the following parameters for the MNIST dataset: | ||
+ | patchSize: 28x28 patches | ||
sparsityParam = 0.1 | sparsityParam = 0.1 | ||
lambda = 3e-3 | lambda = 3e-3 | ||
beta = 3 | beta = 3 | ||
- | normalizeData | + | normalizeData: linear scaling (patches = patches / 255) |
The autoencoder should learn pen strokes as features. These features should start to become obvious after 400 iterations of minFunc, which takes around 20 - 25 minutes on the Corn cluster. Visualised, the features look as follows: | The autoencoder should learn pen strokes as features. These features should start to become obvious after 400 iterations of minFunc, which takes around 20 - 25 minutes on the Corn cluster. Visualised, the features look as follows: |