Questions tagged [attention]

For questions about the concept of attention in artificial intelligence and machine learning. Attention-like mechanisms were successfully used in natural language processing and computer vision tasks, such as machine translation. For a review of attention-based mechanism used in NLP, take a look at "Attention in Natural Language Processing" by Andrea Galassi et al.

Filter by
Sorted by
Tagged with
0
votes
1answer
86 views

What is input (and shape) to K/V/Q of self-attention of EACH Decoder block of Language-translation model Transformer's tokens during Inference?

Transformer model of the original Attention paper has a decoder unit that works differently during Inference than Tranining. I'm trying to understand the shapes used during decoder (both self-...
1
vote
1answer
27 views

Is there a notion of location in Transformer architecture in subsequent self-attention layers?

Transformer architecture (without position embedding) is by the very construction equivariant to the permutation of tokens. Given query $Q \in \mathbb{R}^{n \times d}$ and keys $K \in \mathbb{R}^{n \...
1
vote
0answers
31 views

Why does research on faster Transformers focus on the query-key product?

A lot of recent research on Transformers has been devoted to reducing the cost of the self-attention mechanism: $$\text{softmax}\left(\frac{Q K^T}{\sqrt{d}} \right)V,$$ As I understand it, the runtime,...
2
votes
2answers
132 views

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

I heard from many people about the paper titled Attention Is All You Need by Ashish Vaswani et al. What actually does the "attention" do in simple terms? Is it a function, property, or some ...
0
votes
0answers
23 views

Is the multi-head attention in the transformer a weighted adjacency matrix?

Are multi-head attention matrices weighted adjacency matrices? The job of the multi-head-attention mechanism in transformer models is to determine how likely a word is to appear after another word. In ...
1
vote
0answers
31 views

Are there any benefits of adding attention to linear layers?

Is attention useful only in transformer/convolution layers? Can I add it to linear layers? If yes, how (on a conceptual level, not necessarily the code to implement the layers)?
1
vote
0answers
31 views

Is there a proper initialization technique for the weight matrices in multi-head attention?

Self-attention layers have 4 learnable tensors (in the vanilla formulation): Query matrix $W_Q$ Key matrix $W_K$ Value matrix $W_V$ Output matrix $W_O$ Nice illustration from https://jalammar....
2
votes
1answer
173 views

Why does a transformer not use an activation function following the multi-head attention layer?

I was hoping someone could explain to me why in the transformer model from the "Attention is all you need" paper there is no activation applied after both the multihead attention layer and ...
0
votes
0answers
19 views

How to get Attention Maps from Attention Gates in Attention UNET?

Contex I have Attention UNET for image segmentation. I use it for humans segmentation. Question Everything works fine. I want to get attention maps from my network, so I could see what my UNET is ...
1
vote
0answers
36 views

Couldn't the self-attention mechanism be replaced with a global depth-wise convolution?

The main advantages of the self-attention mechanism are: Ability to capture long-range dependencies Ease to parallelize on GPU or TPU However, I wonder why the same goals cannot be achieved by ...
0
votes
1answer
23 views

What is the bit memory task?

I learned from this post about the so-called bit memory: They froze its self-attention and feed-forward layers and, in separate copies, fine-tuned peripheral layers on each on a wide range of tasks: ...
0
votes
0answers
14 views

Why do we transform feature vectors in attention modules for CNNs

If we have a set of feature maps with dimensions [B, C, H, W] (batch, channel, height, width), why do we transform our feature maps before we calculate their affinity/correlation in attention ...
0
votes
1answer
51 views

Attention mechanism: Why apply multiple different transformations to obtain query, key, value

I have two questions about the structure of attention modules: Since I work with imagery I will be talking about using convolutions on feature maps in order to obtain attention maps. If we have a set ...
0
votes
1answer
61 views

Why people always say the Transformer is parallelizable while the self-attention layer still depends on outputs of all time steps to calculate?

When compared to an RNN seq-to-seq model, people always say the Transformer is parallelizable. In the original Attention Is All You Need paper, it also said that Recurrent models typically factor ...
1
vote
1answer
598 views

Isn't attention mask for BERT model useless?

I have just dived into deep learning for NLP, and now I'm learning how the BERT model works. What I found odd is why the BERT model needs to have an attention mask. As clearly shown in this tutorial ...
4
votes
1answer
254 views

In Computer Vision, what is the difference between a transformer and attention?

Having been studying computer vision for a while, I still cannot understand what the difference between a transformer and attention is?
1
vote
0answers
47 views

Computing the mean attention distance for ViT

Recently I came across the paper that introduces the Vision Transformer (ViT) "AN IMAGE IS WORTH 16X16 WORDS: TRANSFORMERS FOR IMAGE RECOGNITION AT SCALE". The thing I don't really ...
2
votes
1answer
113 views

Are there any advantages of the local attention against convolutions?

Transformer architectures, based on the self-attention mechanism, have achieved outstanding performance in a variety of applications. The main advantage of this approach is that the given token can ...
0
votes
0answers
15 views

Does the transformers model (in "Attention is All You Need") exclude the encoder in language modelling tasks?

The language model I am referring to is the one outlined in "Attention is All You Need": My understanding is that when the task is translation, the encoder's input could be "Hi, my ...
0
votes
0answers
76 views

How do autoregressive attention mechanism work in multi-headed attention?

[LONG POST!!] I am working on a DNN model that works as an improviser to generate music sequences. The idea of generating music is based on taking a sequence of music nodes (their index representation)...
0
votes
0answers
15 views

Visualizing encoder-attention after ResNet in terms of ResNet input

I have a transform-encoder only architecture, which has the following structure: ...
1
vote
1answer
27 views

How is the variational lower bound for hard attention derived in Show, Attend and Tell

How is the jump from line 1 to line 2 done in equation 10 of Show, Attend and Tell? While we're at it, another thing that might be muddying the waters for me is that I'm not clear on what the sum is ...
2
votes
0answers
24 views

How to Select Model Parameters for Transformer (Heads, number of layers, etc)

Is there a general guideline on how the Transformer model parameters should be selected, or the range of these parameters that should be included in a hyperparameter sweep? Number of heads Number of ...
1
vote
1answer
37 views

Do RNNs/LSTMs really need to be sequential?

There are many articles comparing RNNs/LSTMs and the Attention mechanism. One of the disadvantages of RNNs that is often mentioned is that while Attention can be computed in parallel, RNNs are highly ...
1
vote
0answers
38 views

SAGAN - is there a mistake in the original paper?

in the original paper the following scheme of the self-attention appears: https://arxiv.org/pdf/1805.08318.pdf In a later overview: https://arxiv.org/pdf/1906.01529.pdf this scheme appears: ...
0
votes
1answer
53 views

Can an existing transformer model be modified to estimate the next most probable number in a sequence of numbers?

Models based on the transformer architectures (GPT, BERT, etc.) work awesome for NLP tasks including taking an input generated from words and producing probability estimates of the next word as the ...
5
votes
2answers
452 views

Why does GPT-2 Exclude the Transformer Encoder?

After looking into transformers, BERT, and GPT-2, from what I understand, GPT-2 essentially uses only the decoder part of the original transformer architecture and uses masked self-attention that can ...
1
vote
1answer
70 views

How is the transformers' output matrix size arrived at?

In this tensorflow article, the comments in the code say that MHA should output with one of the dimensions being the sequence length of the query/key. However, that means that the second MHA in the ...
1
vote
0answers
37 views

What does the outputlayer of BERT for masked language modelling look like?

In the tutorial BERT – State of the Art Language Model for NLP the masked language modeling pre-training steps are described as follows: In technical terms, the prediction of the output words ...
6
votes
3answers
1k views

What kind of word embedding is used in the original transformer?

I am currently trying to understand transformers. To start, I read Attention Is All You Need and also this tutorial. What makes me wonder is the word embedding used in the model. Is word2vec or GloVe ...
1
vote
1answer
80 views

What is the purpose of "alignment" in the self-attention mechanism of transformers?

I've been reading about transformers & have been having some difficulty understanding the concept of alignment. Based on this article Alignment means matching segments of original text with their ...
0
votes
1answer
92 views

Reasoning behind performance improvement with hopfield networks

In the paper Hopfield networks is all you need, the authors mention that their modern Hopfield network layers are a good replacement for pooling, GRU, LSTM, and attention layers, and tend to ...
0
votes
1answer
47 views

Factors that causing totally different outcomes from an exactly same model and datasets

Here is a model that trains time series data in (batch, step, features) way. I have kept the random state for train test split function the same. Every parameter below the same, running the model ...
1
vote
0answers
13 views

How are the parameters $\alpha_i$ of hard attention trained?

I have a question about Show, Attend and Tell: Neural Image CaptionGeneration with Visual Attention paper by Xu. The basic mechanism of stochastic hard attention is that each pixel of the input image ...
3
votes
1answer
387 views

What's the difference between content-based attention and dot-product attention?

I'm following this blog post which enumerates the various types of attention. It mentions content-based attention where the alignment scoring function for the $j$th encoder hidden state with respect ...
3
votes
2answers
173 views

Recent deep learning textbook (i.e. covering at least GANs, LSTM and transformers and attention)

I am searching for an academic (i.e. with maths formulae) textbook which covers (at least) the following: GAN LSTM and transformers (e.g. seq2seq) Attention mechanism The closest match I got is Deep ...
0
votes
1answer
60 views

Can the attention mechanism improve the performance in the case of short sequences?

I am aware that the attention mechanism can be used to deal with long sequences, where problems related to gradient vanishing and, more generally, representing effectively the whole sequence arise. ...
1
vote
1answer
124 views

In attention models with multiple layers, are weight matrices shared across layers?

In articles that describe neural architectures with multiple attention layers of the same form, are the weight matrices usually the same across the layers? Consider as an example, "Attention is ...
1
vote
2answers
147 views

In the multi-head attention mechanism of the transformer, why do we need both $W_i^Q$ and ${W_i^K}^T$?

In the Attention is all you need paper, on the 4th page, we have equation 1, which describes the self-attention mechanism of the transformer architecture $$ \text { Attention }(Q, K, V)=\operatorname{...
2
votes
0answers
111 views

How to handle long sequences with transformers?

I have a time series sequence with 10 million steps. In step $t$, I have a 400 dimensional feature vector $X_t$ and a scalar value $y_t$ which I want to predict during inference time and I know during ...
5
votes
2answers
445 views

What is different in each head of a multi-head attention mechanism?

I have a difficult time understanding the "multi-head" notion in the original transformer paper. What makes the learning in each head unique? Why doesn't the neural network learn the same ...
0
votes
1answer
518 views

What is the difference between Attention Gate and CNN filters?

Attention models/gates are used to focus/pay attention to the important regions. According to this paper, the authors describe that a model with Attention Gate (AG) can be trained from scratch. Then ...
1
vote
0answers
326 views

What is the gradient of an attention unit?

The paper Attention Is All You Need describes the Transformer architecture, which describes attention as a function of the queries $Q = x W^Q$, keys $K = x W^K$, and values $V = x W^V$: $\text{...
4
votes
1answer
331 views

What is the cost function of a transformer?

The paper Attention Is All You Need describes the transformer architecture that has an encoder and a decoder. However, I wasn't clear on what the cost function to minimize is for such an architecture. ...
1
vote
1answer
38 views

Is the Decoder mask (triangular mask) applied only in the first decoder block, or to all blocks in Decoder?

The Decoder mask, also called "look-ahead mask", is applied in the Decoder side to prevent it from attending future tokens. Something like this: ...
2
votes
1answer
118 views

Transformers: how to get the output (keys and values) of the encoder?

I was reading the paper Attention Is All You Need. It seems like the last step of the encoder is a LayerNorm(relu(WX + B) + X), i.e. an add + normalization. This should result in a $n$ x $d^{model}$ ...
3
votes
1answer
85 views

Transformers: how does the decoder final layer output the desired token?

In the paper Attention Is All You Need, this section confuses me: In our model, we share the same weight matrix between the two embedding layers [in the encoding section] and the pre-softmax linear ...
4
votes
1answer
99 views

Why are "Transformers" called this way?

What is the reason behind the name "Transformers", for Multi Head Self-Attention-based neural networks from Attention is All You Need? I have been googling this question for a long time, and ...
3
votes
1answer
129 views

Any comparison between transformer and RNN+Attention on the same dataset?

I am wondering what is believed to be the reason for superiority of transformer? I see that some people believe because of the attention mechanism used, it’s able to capture much longer dependencies. ...
5
votes
3answers
1k views

What is the purpose of Decoder mask (triangular mask) in Transformer?

I'm trying to implement transformer model using this tutorial. In the decoder block of the Transformer model, a mask is passed to "pad and mask future tokens in the input received by the decoder&...