Cross Validated

Help Center > Badges > Popular Question

 Popular Question
Question with 1,000 views. This badge can be awarded multiple times.

earned this badge 11 times.
Should one-hot output encoding be used in backpropagation?
Awarded Feb 26 at 10:35
Skip connections: Benefits of skipping extra layers
Awarded Jan 7 at 12:40
Backward propagation without a loop over training examples
Awarded Nov 24 '19 at 3:45
Transfer learning: How and why retrain only final layers of a network?
Awarded Aug 8 '19 at 6:15
Convolution with a non-square kernel
Awarded Apr 8 '19 at 15:20
Working for Logistic regression partial derivatives
Awarded Feb 20 '19 at 16:40
Regularisation: why multiply by 1/2m?
Awarded Feb 3 '19 at 2:45
Difference between pooling and subsampling
Awarded Jan 22 '19 at 2:30
What is the derivative of the ReLU activation function?
Awarded Jul 8 '18 at 15:43
Why is tanh almost always better than sigmoid as an activation function?
Awarded May 29 '18 at 13:10
Etymology of “Adam” algorithm for gradient descent
Awarded Apr 18 '18 at 22:50

Others with this badge