user3668129's user avatar
user3668129's user avatar
user3668129's user avatar
user3668129
  • Member for 3 years, 11 months
  • Last seen more than a week ago
7 votes
1 answer
934 views

Why autoencoders use binary_crossentropy loss and not mean squared error?

4 votes
1 answer
223 views

How FLAIR NER algorithm detects entities with typo?

3 votes
1 answer
5k views

How batch normalization layer resolve the vanishing gradient problem?

2 votes
0 answers
121 views

Convolutional autoencoder - why keras example is asymmetry model?

1 vote
0 answers
18 views

Why FLAIR does't recognize the entire location name

1 vote
1 answer
130 views

In LSTM why h_t output twice?

1 vote
2 answers
55 views

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

1 vote
2 answers
1k views

T-SNE with high number of features

1 vote
0 answers
201 views

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

1 vote
0 answers
30 views

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

1 vote
1 answer
72 views

Why VAE Encoder outputs log variance and not standard deviation?

1 vote
2 answers
731 views

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

1 vote
0 answers
233 views

How Adam optimizer influence the learning rate? [closed]

0 votes
1 answer
101 views

What does the ellipse in Gradient descent describes?

0 votes
1 answer
41 views

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

0 votes
1 answer
100 views

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

0 votes
0 answers
205 views

Which loss function is used on Whisper model?

0 votes
0 answers
28 views

How the embedding model (x-vectors) trained?

0 votes
0 answers
38 views

Why speaker diarization DER on Ego4D dataset is so bad?

0 votes
1 answer
48 views

What is the difference between VAD and Speaker Segmentation?

0 votes
0 answers
23 views

Can we use the pretrained WavLM on Portuguese?

0 votes
0 answers
7 views

How to get / calculate statistics about voxceleb2?

0 votes
0 answers
7 views

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

0 votes
1 answer
20 views

How to get the closest samples to time series dataset?

0 votes
0 answers
10 views

how to get similar traning data for a test sample?

0 votes
1 answer
1k views

What are the differences between bert embedding and flair embedding

0 votes
1 answer
72 views

reprocessing steps for images before training classification models

0 votes
1 answer
22 views

Using vgg16 or inception with wights equals to None

0 votes
0 answers
36 views

GAN model with different optimization functions

0 votes
3 answers
169 views

Why do neural networks with more layers perform better?