New answers tagged

1 vote
Accepted

Is the "Helvetica scenario" mentioned here related to Artificial Intelligence?

The "Helvetica scenario" referenced in the paper is an AI issue related to generative systems failing. In GANs, this might be due to a generator becoming initially strong against the ...
user avatar
  • 23.1k
0 votes

How to decode P bits that represent a random weight generator?

I don't understand why they say with $P$ bits, there's $2*P$ combinations, wouldn't it be $2^P$? I think you are correct here, and would suspect a typesetting issue or typo. I also think that 2Q ...
user avatar
  • 23.1k
2 votes
Accepted

What is the total number of actions and rewards count

TL;DR In the DQN paper, each environment was trained for 50 million frames, grouped in fours without overlap, so there were 12.5 million state, action, reward next-state records used. The above direct ...
user avatar
  • 23.1k
1 vote

What is the right way to find the alphas in this equation?

Equation (7) in the Grad-CAM++ paper is linear. In fact for a given class $c$ we have just one equation and many unknowns (the $\alpha_{ab}^{kc}$), hence the equation is underdetermined and will have ...
user avatar
  • 131
2 votes

What is a 'degenerate run' in evaluating model performance?

The authors explain their use of the term in the paper: Without the bias correction we observe many degenerate runs, where fine-tuned models fail to outperform the random baseline Specifically, as ...
user avatar
  • 23.1k
1 vote
Accepted

What are the steps to derive the original GAN loss function from the generalized version?

There are some definitions that may cause confusion here. In the original GANs (the first formula), the output from the discriminator connects to a sigmoid activation, the second formula is the real ...
user avatar
  • 677

Top 50 recent answers are included