New answers tagged probability-distribution
1
vote
What is the meaning of $p_{\text {data }}(y)$ in the CycleGAN?
I interpret $p_{data}(y)$ as the empirical probability of seeing an image $y$ in the training data.
For example, in a typical training run, each training image is shown to the network the same number ...
2
votes
Accepted
PPO: policy loss becomes nan
You might want to try substituting the exponentiation with a piecewise-defined function that uses a numerical approximation that is more numerically stable for low values of the exponent, such as ...
Top 50 recent answers are included
Related Tags
probability-distribution × 71machine-learning × 20
probability × 12
reinforcement-learning × 11
neural-networks × 7
deep-learning × 6
generative-adversarial-networks × 5
classification × 4
comparison × 4
math × 4
objective-functions × 4
variational-autoencoder × 4
proximal-policy-optimization × 4
notation × 4
random-variable × 4
bayesian-networks × 4
terminology × 3
datasets × 3
papers × 3
expectation × 3
kl-divergence × 3
maximum-likelihood × 3
iid × 3
convolutional-neural-networks × 2
definitions × 2