Edoardo Guerriero's user avatar
Edoardo Guerriero's user avatar
Edoardo Guerriero's user avatar
Edoardo Guerriero
  • Member for 3 years, 9 months
  • Last seen more than a week ago
58 votes
Accepted

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

29 votes

What is the intuition behind the dot product attention?

24 votes

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

9 votes

Using AI to extend an imagine pattern

8 votes
Accepted

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

7 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

Why are reinforcement learning methods sample inefficient?

5 votes

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

5 votes
Accepted

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

5 votes

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

5 votes
Accepted

How does AI 'see' the images it generates- from what perspective?

4 votes

How should I read a deep learning paper?

4 votes

Loss function for choosing a subset of objects

4 votes

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

4 votes

When can I call an entity a hyperparameter?

4 votes

Learning an identity function with convolutional networks

4 votes
Accepted

Solving logical pattern puzzles with Machine Learning?

4 votes

Strange artifacts in autoencoder outputs

3 votes
Accepted

What is the definition of a "model"?

3 votes

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

3 votes
Accepted

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

3 votes
Accepted

What is the difference between representation and embedding?

3 votes

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

3 votes

Examples where AI fails in revealing ways

3 votes
Accepted

What loss function should I use if I only care about the accuracy of one class?

3 votes

How to convert color information to 1D feature vector?

3 votes
Accepted

Why do we multipy context_size with embedding_dim? (PyTorch)

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?

1
2 3 4 5 6