Exercise: Implement deep networks for digit classification

From Ufldl

Jump to: navigation, search
(Step 4: Implement fine-tuning)
m (Step 4: Implement fine-tuning)
Line 48: Line 48:
'''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.
-
'''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.
+
'''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.
=== Step 5: Test the model ===
=== Step 5: Test the model ===

Revision as of 22:04, 15 May 2011

Personal tools