New answers tagged relu
2
votes
Accepted
Does it make sense to provide a DQN with negative rewards for a network with relu and sigmoid activations?
A network with ReLU activation can predict negative values; we put ReLU between the hidden layers but return the output of the final layer without any activation function, or with a linear activation ...
Top 50 recent answers are included
Related Tags
relu × 41neural-networks × 22
activation-functions × 18
convolutional-neural-networks × 13
deep-learning × 10
backpropagation × 9
machine-learning × 7
sigmoid × 5
comparison × 2
tensorflow × 2
math × 2
optimization × 2
reinforcement-learning × 1
reference-request × 1
recurrent-neural-networks × 1
dqn × 1
gradient-descent × 1
deep-neural-networks × 1
image-processing × 1
rewards × 1
regression × 1
convolution × 1
convergence × 1
function-approximation × 1
feedforward-neural-networks × 1