Exercise: Implement deep networks for digit classification
From Ufldl
(→Step 3: Train the softmax classifier on the L2 features) |
(→Step 4: Implement fine-tuning) |
||
Line 46: | Line 46: | ||
{{Quote| | {{Quote| | ||
Note: When adding the weight decay term to the cost, you should regularize '''all''' the weights in the network. | Note: When adding the weight decay term to the cost, you should regularize '''all''' the weights in the network. | ||
+ | }} | ||
+ | |||
+ | {{Quote| | ||
+ | Implementation Tip: It is always a good idea to implement the code modularly and check (the gradient) of each part of the code before writing the more complicated parts. | ||
}} | }} | ||