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
51 views

Is stability an attribute of model or training algorithm used or combination of both?

1 vote
1 answer
1k views

Is there any difference between an objective function and a value function?

1 vote
1 answer
531 views

Why many deep learning research papers continue to be in arXiv?

1 vote
0 answers
249 views

Is image generation not existent before generative adversarial networks?

1 vote
0 answers
44 views

Example for batch normalization in an aritifical neural network

1 vote
0 answers
48 views

Are there any other metrics available for calculating the distance between two probability distributions other than those mentioned?

1 vote
0 answers
22 views

Is there any concept like 'applying affine transformation on multiple inputs'?

1 vote
2 answers
28 views

Why not undefined expression is different from numerical underflow?

1 vote
0 answers
94 views

Which product operation should be used in affine transformation?

1 vote
2 answers
2k views

Are mean and standard deviation in variational autoencoders unique?

1 vote
1 answer
41 views

What is the high-level algorithm followed by contemporary packages for the calculation of gradient?

1 vote
1 answer
83 views

What all does the gradient tells us other than the direction to move parameters?

1 vote
0 answers
50 views

Is it true that real world data is highly discontinuous?

1 vote
1 answer
46 views

Which class of functions are quite complicated in deep learning?

1 vote
2 answers
826 views

What does it mean "having Lipschitz continuous derivatives"?

1 vote
1 answer
71 views

Is there any significance for higher order gradients in artificial intelligence?

1 vote
1 answer
388 views

Can I always interpret features as random variables in machine learning safely?

1 vote
1 answer
140 views

Is there any simple example for volumetric data except from physics and medicine?

1 vote
0 answers
23 views

What are the types of data in which the order of instances does matter?

1 vote
0 answers
20 views

Are there any recommendations on initialising a single parameter in deep learning?

1 vote
0 answers
252 views

Why batch normalization before upsampling is giving worse results?

1 vote
0 answers
76 views

Is the capability of RNN more than the capability of MLP?

1 vote
1 answer
582 views

Is a recurrent layer same as LSTM or single-layered LSTM?

1 vote
0 answers
79 views

What does "statistical strength" mean in this context?

1 vote
1 answer
47 views

When does an RNN use the connections that help in going backward in time?

1 vote
1 answer
2k views

What exactly is embedding layer used in RNN encoders?

1 vote
1 answer
212 views

Are the capabilities of connectionist AI and symbolic AI the same?

1 vote
0 answers
76 views

Does Godel's incompleteness theorems restricts the scope of connectionist-AI?

1 vote
1 answer
306 views

Mathematically speaking, Is it only the product operation used in the chain rule causing the vanishing or exploding gradient?

1 vote
1 answer
391 views

What is meant by "spatial encoding" in the context of convolutional neural networks?

1
3 4
5
6 7
10