Exercise: Implement deep networks for digit classification
From Ufldl
(→Step 4: Implement fine-tuning) |
(→Step 4: Implement fine-tuning) |
||
Line 47: | Line 47: | ||
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| | {{Quote| |