Search Results
| Search type | Search syntax |
|---|---|
| Tags | [tag] |
| Exact | "words here" |
| Author |
user:1234 user:me (yours) |
| Score |
score:3 (3+) score:0 (none) |
| Answers |
answers:3 (3+) answers:0 (none) isaccepted:yes hasaccepted:no inquestion:1234 |
| Views | views:250 |
| Code | code:"if (foo != bar)" |
| Sections |
title:apples body:"apples oranges" |
| URL | url:"*.example.com" |
| Saves | in:saves |
| Status |
closed:yes duplicate:no migrated:no wiki:no |
| Types |
is:question is:answer |
| Exclude |
-[tag] -apples |
| For more details on advanced search visit our help page | |
Results tagged with deep-learning
Search options not deleted
user 133184
a new area of Machine Learning research concerned with the technologies used for learning hierarchical representations of data, mainly done with deep neural networks (i.e. networks with two or more hidden layers), but also with some sort of Probabilistic Graphical Models.
0
votes
0
answers
153
views
Why are we training Segment Embedding in BERT?
In BERT we have segment embeddings that are used for "Segment Embeddings with shape (1, n, 768) which are vector representations to help BERT distinguish between paired input sequences."
Yes, but why. …
- 111
0
votes
1
answer
78
views
What is the difference between adding words to a tokenizer and training a tokenizer?
The title says it all. I was researching this question but couldn't find something useful. What is the difference between adding words to a tokenizer and training a tokenizer?
- 111
0
votes
0
answers
567
views
Slow and Fast tokenizer gives different outputs(sentencepiece tokenizer)
When i use T5TokenizerFast(Tokenizer of T5 arcitecture), the output is expected as follows:
['▁', '</s>', '▁Hello', '▁', '<sep>', '</s>']
But when i use normal tokenizer, it starts to split special t …
- 111
2
votes
1
answer
7k
views
How special tokens in BERT-Transformers work?
I was trying to understand how tokens work and all I understood is that tokens are the representation of the input in a more meaningful way (data preparation for the "encoder of transformer" or "BERT" …
- 111
1
vote
1
answer
163
views
Which representation of CNN feature maps is correct?
When I extract my features from my CNN, it doesn't look like this:
And those pictures are not just representation. From this article it can be seen that these features are actual extracted features f …
- 111
0
votes
1
answer
214
views
Smaller embedding size causes lower loss
When I convert my multilingual transformer model to a single lingual transformer model (got my languages embedding from the multilingual transformer and deleted other embeddings, decreased dimensions …
- 111
0
votes
1
answer
66
views
One word changes everything NLP
I have a classification model (BERT) that classifies sentences as either question or normal sentences. But whenever a sentence has "how" word, the model chooses "question" class.
How can I solve this …
- 111
1
vote
1
answer
4k
views
Should i always transform data to normal distribution?
I am trying to understand transformations but this question seems to be in my and some people's mind. If we have a numeric variable in EVERY data science case. Transforming data(Log, power transforms) …
- 111
0
votes
1
answer
59
views
Transpose Convolution feature extraction
Convolution extracts high-level features, but what about Transpose Convolution (or De/Up-Convolution)? Does it behave exactly the opposite? Does it generate lower-level features?
- 111
0
votes
0
answers
331
views
Using BERT embeddings as input for transformer architecture
I will use BERT's embedding weights (as discussed here) for embedding in embedding layers of the transformer model. But my question is: don't embeddings of BERT already go through the whole encoding l …
- 111
1
vote
1
answer
760
views
High level-Low Level features in U-NET
Why do the first layers of U-Net or CNN generate low-level features? Why not the last layers? What is the logic behind getting low-level features at the beginning of architecture? And yes, high-level …
- 111
1
vote
1
answer
64
views
Is backpropagation applied every layer the same?
For example, I have layers that are pretrained. But while predicted, the loss is very high. But not because of pre-trained layers. Because of not pretrained layers. Will every layer be affected by bac …
- 111
0
votes
1
answer
62
views
Increasing/Decreasing importance of feature/thing in ML/DL
I have 3 cases:
I have a classification model that will be used to classify cats and dogs. On my train data dog pictures has a watermark on them, but cat pictures don't. The problem is: Whenever I ha …
- 111
0
votes
1
answer
295
views
Weird consequence of not freezing layers in Neural Network
I was researching about "why are we freezing layers" and I came across the answer says "to not lose the information of pre-trained model" But; we are just freezing early layers (I know why). For examp …
- 111
2
votes
0
answers
148
views
MinMaxScaler makes my prediction flat
I am trying to do univariate forecasting. But when i try to use MinMax Scaler my predictions are being flat (tried to use different activation functions) but when i use Standart Scaler my predictions …
- 111