Darren Cook's user avatar
Darren Cook's user avatar
Darren Cook's user avatar
Darren Cook
  • Member for 8 years, 7 months
  • Last seen this week
9 votes
Accepted

Why deep learning models still use RELU instead of SELU, as their activation function?

8 votes

Transformer model: Why are word embeddings scaled before adding positional encodings?

4 votes
Accepted

Does multi-head attention remove the need for self-attention?

3 votes

Can we fine-tune a model on the same dataset which it is pretrained on?

3 votes

Choosing best model produced from different algorithms. Metric produced by cross-validation on the train set or metric produced on the test set?

3 votes
Accepted

What reccent alternatives to LSTM are there for regression problems?

2 votes
Accepted

Approximation of long sequence of layers by one layer

2 votes

How to make sure that the features learned by a neural network are not correlated?

2 votes
Accepted

Question on embedding similarity / nearest neighbor methods [SCANN Paper]

2 votes
Accepted

Is roc auc graph better than roc auc score? If yes why?

2 votes

Identifying competition climbing styles from World Cup data

2 votes

Why cant we use normalise position encodings instead of the cos and sine encodings used in the Transformer paper?

1 vote

Recommended way to embed a text thousands of tokens long?

1 vote

Transformer model is very slow and doesn't predict well

1 vote

What does it mean order of input sequence does not matter for transformer self-attention head?

1 vote
Accepted

Why is T5 often used in text-to-data for text prompt encoders?

1 vote

torch cuda not able to identify gpu on aws g4dn.xlarge

1 vote
Accepted

How to control a decision tree?

1 vote

How to classify text and predict if it belongs to the group or not?

1 vote
Accepted

What ML techniques could be used for biometric feature extraction and ID generation?

1 vote
Accepted

Im looking for good neurons silmilarity metric

1 vote
Accepted

Transformers for time series - what is the role of the encoder?

1 vote
Accepted

Feature engineering of timestamp for time series analysis

1 vote

Which ML approach is the best for huge state spaces?

1 vote

Find smooth global maximum from noisy points

1 vote

Mixed language OCR

1 vote

Is big data a fallacy if most phenomena can be mostly described by few variables?

1 vote

Why do the performance of DL models increase with the volume of data while that of ML models will flat out or even decrease?

1 vote
Accepted

Organising the preprocessing of a dataset that will be consumed by multiple models

1 vote

How BERT model differentiate words with different meanings?