Skip to main content
noe's user avatar
noe's user avatar
noe's user avatar
noe
  • Member for 8 years, 7 months
  • Last seen this week
58 votes
Accepted

Why are Machine Learning models called black boxes?

52 votes

Why does Keras need TensorFlow as backend?

31 votes
Accepted

Why is the decoder not a part of BERT architecture?

27 votes
Accepted

What is a channel in a CNN?

23 votes

ChatGPT's Architecture - Decoder Only? Or Encoder-Decoder?

22 votes
Accepted

Can BERT do the next-word-predict task?

20 votes
Accepted

Why are autoencoders for dimension reduction symmetrical?

19 votes
Accepted

GANs (generative adversarial networks) possible for text as well?

18 votes

Why do convolutional neural networks work?

18 votes

Is the Transformer decoder an autoregressive model?

18 votes
Accepted

Why does prompt engineering work, since prompt engineering questions don't appear as training data?

17 votes

Neural Network for Multiple Output Regression

16 votes
Accepted

model.cuda() in pytorch

16 votes
Accepted

What is the difference between active learning and reinforcement learning?

16 votes
Accepted

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

15 votes
Accepted

Is BERT a language model?

14 votes
Accepted

How pre-trained BERT model generates word embeddings for out of vocabulary words?

14 votes
Accepted

What are the inputs to the first decoder layer in a Transformer model during the training phase?

14 votes
Accepted

Is (manual) feature extraction outdated?

13 votes
Accepted

Detecting anomalies with neural network

12 votes
Accepted

In a Transformer model, why does one sum positional encoding to the embedding rather than concatenate it?

11 votes
Accepted

How is GPT able to handle large vocabularies?

11 votes
Accepted

what is the first input to the decoder in a transformer model?

11 votes
Accepted

Minimal working example or tutorial showing how to use Pytorch's nn.TransformerDecoder for batch text generation in training and inference modes?

11 votes
Accepted

How high of a correlation coefficient of a feature with a target variable is considered too high?

10 votes
Accepted

Variable input/output length for Transformer

10 votes
Accepted

Monitoring machine learning models in production

9 votes
Accepted

Why does vanilla transformer has fixed-length input?

9 votes
Accepted

What is the difference between GPT blocks and Transformer Decoder blocks?

9 votes
Accepted

What is the difference between BERT and Roberta

1
2 3 4 5
26