Exercise:Learning color features with Sparse Autoencoders
From Ufldl
(→Learning color features with Sparse Autoencoders) |
(→Step 2: Learn features on small patches) |
||
Line 44: | Line 44: | ||
<tr><td>[[File:cnn_Features_Bad1.png|240px]]</td><td>[[File:cnn_Features_Bad2.png|240px]]</td></tr> | <tr><td>[[File:cnn_Features_Bad1.png|240px]]</td><td>[[File:cnn_Features_Bad2.png|240px]]</td></tr> | ||
</table> | </table> | ||
+ | |||
+ | The learned features will be saved to <tt>STL10Features.mat</tt>, which will be used in the later [[Exercise:Convolution and Pooling | exercise on convolution and pooling]]. |