New answers tagged backpropagation
2
votes
Accepted
Does this article make use of the chain rule? And where?
Unless the derivation has been added in a comment, when you read code implementations of backpropagation, then the chain rule has already been used to derive the update rules. As it is basically a ...
2
votes
Accepted
In multilayer perceptron neural networks, are the names "delta", "gradient" and "error" all the same thing? or not?
The terms "error", "delta" and "gradient" in neural network back-propagation are often used as shorthand, or loose explanations for the same thing. This is not strictly ...
Top 50 recent answers are included
Related Tags
backpropagation × 270neural-networks × 156
deep-learning × 59
gradient-descent × 48
machine-learning × 42
convolutional-neural-networks × 36
training × 20
reinforcement-learning × 16
objective-functions × 16
math × 14
feedforward-neural-networks × 12
recurrent-neural-networks × 11
activation-functions × 9
weights × 9
relu × 9
optimization × 8
gradient × 8
cross-entropy × 7
calculus × 7
reference-request × 6
terminology × 6
python × 6
policy-gradients × 6
deep-neural-networks × 6
stochastic-gradient-descent × 6