Skip to main content
hanugm's user avatar
hanugm's user avatar
hanugm's user avatar
hanugm
  • Member for 5 years, 8 months
  • Last seen more than a week ago
7 votes
1 answer
16k views

Which tasks are called as downstream tasks?

6 votes
3 answers
5k views

What is Lipschitz constraint and why it is enforced on discriminator?

5 votes
2 answers
6k views

How to check whether my loss function is convex or not?

5 votes
3 answers
5k views

In logistic regression, why is the binary cross-entropy loss function convex?

5 votes
2 answers
427 views

Is an embedding a representation of a word or its meaning?

5 votes
4 answers
2k views

What is the fundamental difference between an ML model and a function?

5 votes
1 answer
495 views

What does "statistical efficiency" mean in this context?

5 votes
3 answers
6k views

Can I always use "encoding" and "embedding" interchangeably?

5 votes
1 answer
5k views

Is there a widely accepted definition of the width of a neural network?

4 votes
1 answer
5k views

What exactly happens in gradient clipping by norm?

4 votes
1 answer
413 views

What is the stride information of an image referring here?

4 votes
2 answers
1k views

Can I apply reparametrization trick on "any" deep neural network?

4 votes
1 answer
235 views

Is there any relation between the recursive neural network and recurrent neural network?

4 votes
1 answer
293 views

How is the state-value function expressed as a product of sums?

4 votes
1 answer
2k views

Where do the feature extraction and representation learning differ?

4 votes
0 answers
2k views

What is the fundamental difference between max pooling and adaptive max pooling used in PyTorch

4 votes
1 answer
1k views

What are the necessary mathematical properties to be a loss function in gradient based optimizations?

3 votes
1 answer
2k views

What exactly is an XPU?

3 votes
2 answers
296 views

Why do we commonly use the $\log$ to squash frequencies?

3 votes
1 answer
1k views

Why is tanh a "smoothly" differentiable function?

3 votes
1 answer
522 views

Why is the input layer of a neural network usually not counted?

3 votes
2 answers
2k views

Is there any difference between affine transformation and linear transformation?

3 votes
2 answers
295 views

Example of lemma having multiple boldface forms

3 votes
1 answer
850 views

Is there any difference between ConvNet and CNN?

3 votes
1 answer
329 views

How can a probability density value be used for the likelihood calculation?

3 votes
1 answer
234 views

How do AI researchers imagine higher dimensions?

3 votes
1 answer
1k views

What is numerical stability?

3 votes
1 answer
436 views

Is there any way to train a neural network without using gradients?

3 votes
2 answers
122 views

What are the mathematical properties of natural exponential function that lead to its usefulness in artificial intelligence?

3 votes
2 answers
1k views

In layman terms, what does "attention" do in a transformer?

1
2 3 4 5
10