Questions tagged [attention]

For questions related to attention based AI approaches, including gating at the network cell level, selection of models within a model container, virtual pan and zoom within an image field, selection of FFT window size based on expected audio frequency range, setting of criteria to trigger modification of processing priorities, and other mechanisms for changing the focus of attention.

23 questions with no upvoted or accepted answers
Filter by
Sorted by
Tagged with
4
votes
0answers
232 views

What is the difference between GAT and GaAN?

I was looking at two papers Graph Attention Networks (GAT) by Petar Veličković and GaAN: Gated Attention Networks for Learning on Large and Spatiotemporal Graphs by Jiani Zhang. I'm trying to ...
3
votes
0answers
107 views

What is the intuition behind the calculation of the similarity between encoder and decoder states?

Suppose that we are doing machine translation. We have a conditional language model with attention where we are are trying to predict a sequence $y_1, y_2, \dots, y_J$ from $x_1, x_2, \dots x_I$: $$P(...
2
votes
1answer
56 views

What are the keys and values of the attention model for the encoder and decoder in the “Attention Is All You Need” paper?

I have recently encountered the paper on NLP. It is very new to me and I am still unable to see how that works. I have used all the resources over there from the original paper to Youtube videos and ...
2
votes
0answers
20 views

How is visual attention mechanism different from a two branch convolutional neural network?

I am doing some research on the visual attention mechanism in remote sensing domain (where the features learnt from one layer are highlighted using the attention mask derived from another layer). From ...
2
votes
0answers
59 views

What is the time complexity of the forward pass and back-propagation of the sequence-to-sequence model with and without attention?

I keep looking through the literature, but can't seem to find any information regarding the time complexity of the forward pass and back-propagation of the sequence-to-sequence RNN encoder-decoder ...
2
votes
0answers
23 views

Impact or applications of introducing attention in deep networks modelling multi-agent systems

I have been reading quite a lot about the research progress in the domain of self attention-based neural networks that were introduced by Google Inc. in their paper titled "Attention is all you ...
2
votes
0answers
134 views

Why is the transformer for time series forecasting faster than RNN?

I've been reading different papers which implements the Transformer for time series forecasting. Most of the them are claiming that the training time is significantly faster then using a normal RNN. ...
2
votes
0answers
41 views

What is the difference between Squeeze-and-excite and bottleneck modules from Mobilenet v2?

Squezee-and-excite networks introduced SE blocks, while MobileNet v2 introduced linear bottlenecks. What is the effective difference between these two concepts? Is it only implementation (depth-wise ...
2
votes
0answers
80 views

Understanding CNN+LSTM concept with attention and need help

I have a question about the context of CNN and LSTM. I have trained a CNN network for image classification. However, I would like to combine it with LSTM for visualizing the attention weights. So, I ...
2
votes
1answer
70 views

Does GraphSage use hard attention?

I was reading the recent paper Graph Representation Learning via Hard and Channel-Wise Attention Networks, where the authors claim that there is no hard attention operator for graph data. From my ...
2
votes
0answers
137 views

Why does the BERT encoder have an intermediate layer between the attention and neural network layers with a bigger output?

I am reading the BERT paper BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding. As I look at the attention mechanism, I don't understand why in the BERT encoder we have ...
2
votes
0answers
125 views

How do the sine and cosine functions encode position in the transformer?

After going through both the "Illustrated Transformer" and "Annotated Transformer" blog posts, I still don't understand how the sinusoidal encodings are representing the position of elements in the ...
1
vote
0answers
23 views

How to understand the matrices used in the Attention layer?

Attention-scoring mechanism seems to be a commonly-used component in various seq2seq models, and I was reading about the original "Location-based Attention" in Bahadanau well-known paper at https://...
1
vote
1answer
52 views

Why does this multiplication of $Q$ and $K$ have a variance of $d_k$, in scaled dot product attention?

In scaled dot product attention, we scale our outputs by dividing the dot product by the square root of the dimensionality of the matrix: The reason why is stated that this constrains the ...
1
vote
0answers
14 views

How positional encoding works?

In transformer model; to incorporate positional information of texts the researchers have added a positional encoding to the model. How is positional encoding works? How positional encoding system ...
1
vote
1answer
30 views

time-series prediction : loss going down, then stagnates with very high variance

I am trying to design a model based on LSTM cells to do time-series prediction. The ouput value is an integer in [0,13]. I have noticed that one-hot encoding it and ...
1
vote
1answer
60 views

How does transformer leverage GPU which trains faster than RNN?

How does transformer leverage GPU which trains faster than RNN? I understand the parameter space of the transformer might be significantly larger than that of the RNN. But why does the transformer ...
0
votes
0answers
15 views

Where can I place an attention module for different computer vision tasks?

Where can I place an attention module for different computer vision tasks? For example, in this Github issue, the author is not sure where to place the attention module. Are there any rules or best ...
0
votes
1answer
19 views

What is the big fuzz about SHA-RNN versus Transformers?

In his paper introducing SHA-RNN (https://arxiv.org/pdf/1911.11423.pdf) Stephen Merity states that neglecting one direction of research (in this case LSTMs) over another (transformers) merily because ...
0
votes
0answers
6 views

Which model structure is best suited to build a Math OCR (img2latex)? RAM, DRAM, CRNN or Attention OCR?

I am trying to build an OCR which can read the Mathematical equations just like MAthPix and im2markup. im2markup by HarvardNLP seems like a good model but the thing is that it is built using Torch and ...
0
votes
1answer
17 views

Transformers - is the self attention matrix softmax output (layer 1) symmetric?

Let's assume, that we embedded a vector of length 49 into a matrix using 512-d embeddings. If we then multiply the matrix by it transposed version we receive a matrix of 49 by 49. Which is symmetric. ...
0
votes
0answers
7 views

How many spectrogram frames per input character does text-to-speech (TTS) system Tacotron-2 generate?

I've been reading on Tacotron-2, a text-to-speech system, that generates speech just-like humans (indistinguishable from humans) using the GitHub https://github.com/Rayhane-mamah/Tacotron-2. I'm very ...
0
votes
0answers
51 views

Why don't people use nonlinear activation functions after projecting the query key value in attention?

Why don't people use nonlinear activation functions after projecting the query key value in attention? It seems like doing this would lead to much-needed nonlinearity, otherwise, we're just doing ...