2
votes
Accepted
Why use ReLU over Leaky ReLU?
Your understanding or Leaky ReLU is correct, and, yes, it has been proposed to mitigate the dying neurons issue in ReLU: when these are negative, they got zeroed.
Regarding the answer of @Regresslt:
...
1
vote
Why use ReLU over Leaky ReLU?
Leaky ReLU is indeed an improvement over the standard ReLU activation function, but comes with some of the following limitations:
It may suffer from the "dying ReLU" problem, where a large ...
Only top scored, non community-wiki answers of a minimum length are eligible
Related Tags
activation-functions × 160neural-networks × 102
deep-learning × 40
machine-learning × 27
relu × 22
sigmoid × 12
convolutional-neural-networks × 11
objective-functions × 10
math × 10
terminology × 9
backpropagation × 9
regression × 8
perceptron × 8
reinforcement-learning × 7
comparison × 7
deep-neural-networks × 7
function-approximation × 7
hyper-parameters × 6
artificial-neuron × 6
softmax × 6
network-design × 6
classification × 5
gradient-descent × 5
hidden-layers × 5
universal-approximation-theorems × 5