Exercise:Vectorization
From Ufldl
(→Step 2: Learn features for handwritten digits) |
(→Step 2: Learn features for handwritten digits) |
||
Line 30: | Line 30: | ||
patches = first 10000 images from the MNIST dataset | patches = first 10000 images from the MNIST dataset | ||
- | After 400 iterations of updates using minFunc, your autoencoder should have learned features that resemble pen strokes. Our implementation takes around 15-20 minutes on a fast machine. Visualized, the features should look like | + | After 400 iterations of updates using minFunc, your autoencoder should have learned features that resemble pen strokes. In other words, this has learned to represent handwritten characters in terms of what pen strokes appear in an image. Our implementation takes around 15-20 minutes on a fast machine. Visualized, the features should look like the following image: |
[[File:mnistVectorizationEx.png|400px]] | [[File:mnistVectorizationEx.png|400px]] |