**k-Sparse Autoencoders** are autoencoders with linear activation function, where in hidden layers only the $k$ highest activities are kept. This achieves exact sparsity in the hidden representation. Backpropagation only goes through the the top $k$ activated units. This can be achieved with a [ReLU](https://paperswithcode.com/method/relu) layer with an adjustable threshold.

**mt5** is a multilingual variant of [T5](https://paperswithcode.com/method/t5) that was pre-trained on a new Common Crawl-based dataset covering $101$ languages.

mT5: A massively multilingual pre-trained text-to-text transformer

k-Sparse Autoencoder

k-Sparse Autoencoders

**Inception-v4** is a convolutional neural network architecture that builds on previous iterations of the Inception family by simplifying the architecture and using more inception modules than [Inception-v3](https://paperswithcode.com/method/inception-v3).

Source	k-Sparse Autoencoders
Year	2000
Data Source	CC BY-SA - https://paperswithcode.com