New answers tagged sigmoid
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
sigmoid × 28neural-networks × 14
activation-functions × 11
relu × 5
machine-learning × 4
deep-learning × 4
backpropagation × 4
classification × 3
long-short-term-memory × 3
softmax × 3
artificial-neuron × 2
accuracy × 2
reinforcement-learning × 1
tensorflow × 1
keras × 1
recurrent-neural-networks × 1
dqn × 1
objective-functions × 1
definitions × 1
gradient-descent × 1
deep-neural-networks × 1
algorithm × 1
rewards × 1
implementation × 1
computational-learning-theory × 1