User user3668129

0 votes

1 answer

126 views

What is the right Pytorch RNN implementation?

asked Jun 30, 2022 at 8:00

0 votes

1 answer

47 views

The meaning of P and degree of freedom in T-Test

asked Jan 26, 2023 at 11:07

1 vote

1 answer

159 views

Why VAE Encoder outputs log variance and not standard deviation?

asked Dec 26, 2022 at 13:50

0 votes

0 answers

19 views

Feature importance and classes importance

asked Jun 24 at 7:19

0 votes

1 answer

160 views

What can we learn from visualizing Feature Maps

asked Jun 13, 2022 at 14:28

0 votes

1 answer

29 views

can we use tanh activation function to detect outliers?

asked Apr 11 at 12:53

0 votes

0 answers

7 views

Speaker Verification models on

asked Mar 28 at 13:30

1 vote

3 answers

393 views

Why do neural networks with more layers perform better?

asked Dec 3, 2022 at 17:39

3 votes

2 answers

1k views

Does settings $\beta_1 = 0$ or $\beta_2 = 0$ means that ADAM behaves as RMSprop or Momentum?

asked Dec 13, 2022 at 12:52

0 votes

0 answers

20 views

how to get similar traning data for a test sample?

asked Feb 15 at 11:04

0 votes

1 answer

24 views

How to get the closest samples to time series dataset?

asked Feb 14 at 10:00

0 votes

0 answers

12 views

How to split the data for speaker verification using AAM Softmax loss?

asked Dec 20, 2023 at 14:50

0 votes

0 answers

9 views

How to get / calculate statistics about voxceleb2?

asked Nov 30, 2023 at 8:30

0 votes

0 answers

28 views

Can we use the pretrained WavLM on Portuguese?

asked Sep 20, 2023 at 8:47

0 votes

1 answer

80 views

What is the difference between VAD and Speaker Segmentation?

asked Apr 3, 2023 at 14:50

0 votes

1 answer

115 views

Are there any pre-trained non english model of deepspeech?

asked Mar 4, 2023 at 7:19

0 votes

1 answer

142 views

What does the ellipse in Gradient descent describes?

asked Dec 21, 2022 at 9:22

1 vote

0 answers

290 views

How Adam optimizer influence the learning rate? [closed]

asked Dec 17, 2022 at 15:08

8 votes

1 answer

1k views

Why autoencoders use binary_crossentropy loss and not mean squared error?

asked Jun 29, 2021 at 10:25

1 vote

1 answer

156 views

In LSTM why h_t output twice?

asked Jul 2, 2022 at 16:25

0 votes

1 answer

20 views

Do I need to rescale input labels before training (label values between 20..51)?

asked May 31, 2022 at 12:23

4 votes

1 answer

247 views

How FLAIR NER algorithm detects entities with typo?

asked Feb 5, 2022 at 8:05

1 vote

0 answers

21 views

Why FLAIR does't recognize the entire location name

asked Feb 5, 2022 at 7:55

0 votes

1 answer

2k views

What are the differences between bert embedding and flair embedding

asked Feb 1, 2022 at 11:24

1 vote

0 answers

36 views

Is there a reason not to wirk with AMP (automatic mixed precision)?

asked Dec 5, 2021 at 12:29

1 vote

0 answers

218 views

If the input to the autoencoder is normalized, do we need to use sigmoid on the last layer?

asked Jul 1, 2021 at 18:27

1 vote

2 answers

2k views

T-SNE with high number of features

asked Jun 22, 2021 at 6:01

2 votes

0 answers

127 views

Convolutional autoencoder - why keras example is asymmetry model?

asked Jun 22, 2021 at 10:39

1 vote

2 answers

62 views

What we can learn from the data if PCA scree plot bins are almost the same?

asked Jun 13, 2021 at 12:52

3 votes

1 answer

6k views

How batch normalization layer resolve the vanishing gradient problem?

asked Jun 2, 2021 at 4:40

Stack Exchange Network

33 Questions

What is the right Pytorch RNN implementation?

The meaning of P and degree of freedom in T-Test

Why VAE Encoder outputs log variance and not standard deviation?

Feature importance and classes importance

What can we learn from visualizing Feature Maps

can we use tanh activation function to detect outliers?

Speaker Verification models on

Why do neural networks with more layers perform better?

Does settings $\beta_1 = 0$ or $\beta_2 = 0$ means that ADAM behaves as RMSprop or Momentum?

how to get similar traning data for a test sample?

How to get the closest samples to time series dataset?

How to split the data for speaker verification using AAM Softmax loss?

How to get / calculate statistics about voxceleb2?

Can we use the pretrained WavLM on Portuguese?

What is the difference between VAD and Speaker Segmentation?

Are there any pre-trained non english model of deepspeech?

What does the ellipse in Gradient descent describes?

How Adam optimizer influence the learning rate? [closed]

Why autoencoders use binary_crossentropy loss and not mean squared error?

In LSTM why h_t output twice?

Do I need to rescale input labels before training (label values between 20..51)?

How FLAIR NER algorithm detects entities with typo?

Why FLAIR does't recognize the entire location name

What are the differences between bert embedding and flair embedding

Is there a reason not to wirk with AMP (automatic mixed precision)?

If the input to the autoencoder is normalized, do we need to use sigmoid on the last layer?

T-SNE with high number of features

Convolutional autoencoder - why keras example is asymmetry model?

What we can learn from the data if PCA scree plot bins are almost the same?

How batch normalization layer resolve the vanishing gradient problem?