**SqueezeBERT** is an efficient architectural variant of [BERT](https://paperswithcode.com/method/bert) for natural language processing that uses [grouped convolutions](https://paperswithcode.com/method/grouped-convolution). It is much like BERT-base, but with positional feedforward connection layers implemented as convolutions, and grouped [convolution](https://paperswithcode.com/method/convolution) for many of the layers.

**Multi-Head Linear Attention** is a type of linear multi-head self-attention module, proposed with the [Linformer](https://paperswithcode.com/method/linformer) architecture. The main idea is to add two linear projection matrices $E\_{i}, F\_{i} \in \mathbb{R}^{n\times{k}}$ when computing key and value. We first project the original $\left(n \times d\right)$-dimensional key and value layers $KW\_{i}^{K}$ and $VW\_{i}^{V}$ into $\left(k\times{d}\right)$-dimensional projected key and value layers. We then compute a $\left(n\times{k}\right)$ dimensional context mapping $\bar{P}$ using scaled-dot product attention:

$$ \bar{\text{head}\_{i}} = \text{Attention}\left(QW^{Q}\_{i}, E\_{i}KW\_{i}^{K}, F\_{i}VW\_{i}^{V}\right) $$

$$ \bar{\text{head}\_{i}} = \text{softmax}\left(\frac{QW^{Q}\_{i}\left(E\_{i}KW\_{i}^{K}\right)^{T}}{\sqrt{d\_{k}}}\right) \cdot F\_{i}VW\_{i}^{V} $$

Finally, we compute context embeddings for each head using $\bar{P} \cdot \left(F\_{i}{V}W\_{i}^{V}\right)$.

Multi-Head Linear Attention

Linformer: Self-Attention with Linear Complexity

SqueezeBERT

SqueezeBERT: What can computer vision teach NLP about efficient neural networks?

A **Bottleneck Residual Block** is a variant of the [residual block](https://paperswithcode.com/method/residual-block) that utilises 1x1 convolutions to create a bottleneck. The use of a bottleneck reduces the number of parameters and matrix multiplications. The idea is to make residual blocks as thin as possible to increase depth and have less parameters. They were introduced as part of the [ResNet](https://paperswithcode.com/method/resnet) architecture, and are used as part of deeper ResNets such as ResNet-50 and ResNet-101.

Source	SqueezeBERT: What can computer vision teach NLP about efficient neural networks?
Year	2000
Data Source	CC BY-SA - https://paperswithcode.com