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
1 vote
0 answers
24 views

What are all the inputs that support diversity of images in text to image generation?

0 votes
0 answers
8 views

How to quantify the impact of tokenizer output changes on text encoder embeddings?

1 vote
1 answer
66 views

What constitutes a 'backdoor' attack in machine learning models?

3 votes
2 answers
87 views

How does diffusion based text-to-image generation models Mathematically classify inputs to outputs?

3 votes
1 answer
217 views

Understanding the functionality of the switch in the latent diffusion models: Does conditioning information pass to both cross attention and $z_{T}$?

0 votes
0 answers
33 views

Understanding the decreasing influence of text embedding in Text-to-Image diffusion models: A Mathematical perspective

0 votes
0 answers
12 views

Clarification regarding the training status of 'domain specific encoder' in stable diffusion

1 vote
1 answer
53 views

In-depth understanding of formulation and guidance mechanisms in Diffusion models

0 votes
1 answer
352 views

Understanding embedding outputs in transformer models like CLIP

2 votes
1 answer
252 views

Mathematics books for reinforcement learning

0 votes
1 answer
85 views

What should be taken as random variables in the distributions of datasets?

1 vote
0 answers
29 views

Why can't I train like a dataset of samples instead of maintaining replay buffer?

2 votes
1 answer
104 views

How to sample the tuples during the initial time steps of the DDPG algorithm?

1 vote
0 answers
35 views

Does deep RL techniques only interested in 'unit transitions' rather than 'whole experience'?

1 vote
1 answer
57 views

Is it mandatory to multiply every activation of a layer by droupout factor during testing?

1 vote
1 answer
325 views

Can the state transition function be dynamic in reinforcement learning?

1 vote
2 answers
85 views

At which point, does the momentum based GD helps really in this figure?

1 vote
2 answers
62 views

What are all the possible usages of 'multilayer perceptron'?

3 votes
2 answers
260 views

Is there any variant of perceptron convergence algorithm that ensures uniqueness?

0 votes
1 answer
264 views

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

1 vote
0 answers
42 views

Does all GAN's in literature need to satisfy the properties of objective function of initial GAN? [closed]

0 votes
1 answer
80 views

Usability of power series in AI analysis

1 vote
1 answer
62 views

Should I need to interpret the word "metric" in "performance metric" rigorously?

3 votes
2 answers
4k views

What does it mean by "gradient flow" in the context of neural networks?

1 vote
2 answers
255 views

Is there any reason for giving an index to a token based on its frequency in the text?

0 votes
1 answer
48 views

What does it mean by "dynamics of a sequence" mathematically?

0 votes
0 answers
50 views

Does it make sense to compare images (samples) with words (features)?

0 votes
0 answers
215 views

How to visualize the input and output of the GRU cell?

0 votes
1 answer
137 views

Is there any subtle difference between kernel and filter in the context of neural netowrks?

0 votes
1 answer
419 views

Are there any scale invariant activation functions that outputs probability distribution?

1
2 3 4 5
10