8 votes
Accepted

How can the discriminator determine the sample is fake or real?

In a GAN, the discriminator starts untrained, and the generator and discriminator are trained alongside each other. The process relies on neither being too strong for the other at any one stage, so ...
Neil Slater's user avatar
  • 31.7k
4 votes

Would AlphaZero perform better if made with transformers?

Yes! LeelaChessZero, an open-source re-implementation and continuation of AlphaZero, has been experimenting with this for a while now. Their strongest networks are currently transformers, not ...
Todd Sewell's user avatar
3 votes
Accepted

What's the best criterion for evaluating activation maps in a CNN?

It looks like you are thinking about something like UNET architecture. The final layer to your toy problem with a "dot" on the nose can be modelled as a convolution layer from last ...
vl_knd's user avatar
  • 476
2 votes

What's the best criterion for evaluating activation maps in a CNN?

I agree with the answer by @vl_knd and want to add my two cents: This problem does sound a lot like a special case of image segmentation. You want an image where each pixel gets assigned a class. In ...
Chillston's user avatar
  • 1,674
1 vote

Why CNN filters (kernels) are randomly initialized?

It is usual to initialize parameters with "a good guess", when you have prior information, in order to help the model converging. However in deep learning most of the time you have no clue ...
Lelouch's user avatar
  • 171

Only top scored, non community-wiki answers of a minimum length are eligible