user avatar
user avatar
user avatar
Edoardo Guerriero
  • Member for 2 years, 2 months
  • Last seen this week
38 votes
Accepted

Why does the transformer do better than RNN and LSTM in long-range context dependencies?

19 votes

What are the main differences between skip-gram and continuous bag of words?

17 votes

What is the intuition behind the dot product attention?

8 votes
Accepted

What do symmetric weights mean and how does it make backpropagation biologically implausible?

6 votes

What are pros and cons of Bi-LSTM as compared to LSTM?

5 votes

What are some online courses for deep reinforcement learning?

5 votes
Accepted

Why do we need both the validation set and test set?

5 votes

Why are reinforcement learning methods sample inefficient?

5 votes

How can the input order of pairs into a neural network not matter (i.e. symmetry)?

4 votes

In layman terms, what does "attention" do in a transformer?

4 votes

When can I call an entity a hyperparameter?

4 votes

How should I read a deep learning paper?

4 votes

What are some well-known problems where neural networks don't do very well?

4 votes

Loss function for choosing a subset of objects

3 votes
Accepted

How to choosing the random value for parameter w in deep learning network?

3 votes
Accepted

How is the convolution layer is usually implemented in practice?

3 votes
Accepted

How is the Markovian property consistent in reinforcement learning based scheduling?

3 votes
Accepted

What is the type of problem requiring to rate images on a scale?

3 votes

Is possible to train a robot or AI to prune fruit trees?

3 votes
Accepted

Why do we multipy context_size with embedding_dim? (PyTorch)

3 votes

Why doesn't the inception score measure intra-class diversity

3 votes
Accepted

In general - is Stochastic Gradient Descent a "superior" algorithm compared to Gradient Descent?

2 votes

Distinguishing text with opposite meanings in SVM (False Information Detection)

2 votes
Accepted

What is the definition of a "model"?

2 votes

Sequence Embedding using embedding layer: how does the network architecture influence it?

2 votes
Accepted

Additional Optimizations for Convolutional Models On Inferencing

2 votes

Is there any reason for giving an index to a token based on its frequency in the text?

2 votes

Strange artifacts in autoencoder outputs

2 votes

Does a colour consistency loss in neural networks (cycleGAN) make sense?

2 votes
Accepted

Normalizing float prices with movements up to a factor of 100

1
2 3 4 5