Exercise: Implement deep networks for digit classification

From Ufldl

Jump to: navigation, search
(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.
}}
}}

Revision as of 06:04, 10 May 2011

Personal tools