**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).

**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.

k-Sparse Autoencoder

k-Sparse Autoencoders

Inception-v4

Inception-v4, Inception-ResNet and the Impact of Residual Connections on Learning

An **Elastic ResNeXt Block** is a modification of the [ResNeXt Block](https://paperswithcode.com/method/resnext-block) that adds downsamplings and upsamplings in parallel branches at each layer. It is called "elastic" because each layer in the network is flexible in terms of choosing the best scale by a soft policy.

Source	Inception-v4, Inception-ResNet and the Impact of Residual Connections on Learning
Year	2000
Data Source	CC BY-SA - https://paperswithcode.com