New answers tagged

0 votes

What is being optimized with WGAN loss? Is the generator maximizing or minimizing the critic value?

I think I understand what's happening with the loss functions now. Notation: D = discriminator/critic G = generator D(x) - Critic score on real data D(G(z)) - Critic score on fake data ∇_D - Critic ...
user avatar
0 votes

Visualizing the loss landscape in deep NN to compare optimization methods

How about: speed of convergence stability/variance w.r.t to the initial random seed (or other sources of variance like learning rate) presence/number of saddle points in your loss landscape
user avatar
1 vote
Accepted

What does IOU3 mean in this context?

Since we would like to distinguish among IoU values close to 1.0, we use IOU3 as the ground truth score for the SRN. It seems to be just IoU to the power of 3. They use the cube function because they ...
user avatar
  • 136
1 vote

What does IOU3 mean in this context?

From context, I would say: Yes, it's IoU to the power of 3, since they want to have larger differences between values close to 1. Obviously, the difference between ...
user avatar
  • 175
0 votes

What is the domain of the discriminator of a GAN?

Let me try to explain this way, comment if you think it's incorrect. Assume a simple linear function, $y=f(x)=ax+b$ where $a \in \mathbb{R}^*$ and $b\in \mathbb{R}$, each value of $y$ is unique, which ...
user avatar
  • 817
2 votes

What is the domain of the discriminator of a GAN?

Formally, for an input $x$, $D(x)$ gives you the probability of $x$ being real. In this sense $D:\mathcal{X}\rightarrow [0,1]$, where $\mathcal{X}$ is the input space. That said, the output of the ...
user avatar
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 ...
user avatar
  • 66
0 votes

YearPrediction dataset for a regression task: is it possible to evaluate a fair comparison between standard loss and a quadratic one?

The way to evaluate any supervised learning result is to pick a metric - a scoring system for the results. Ideally this metric captures key details of what properties you care about for the trained ...
user avatar
  • 23.8k

Top 50 recent answers are included