**Dense Connections**, or **Fully Connected Connections**, are a type of layer in a deep neural network that use a linear operation where every input is connected to every output by a weight. This means there are $n\_{\text{inputs}}*n\_{\text{outputs}}$ parameters, which can lead to a lot of parameters for a sizeable network.

$$h\_{l} = g\left(\textbf{W}^{T}h\_{l-1}\right)$$

where $g$ is an activation function.

Image Source: Deep Learning by Goodfellow, Bengio and Courville

**Energy Based Processes** extend energy based models to exchangeable data while allowing neural network parameterizations of the energy function. They extend the previously separate stochastic process and latent variable model perspectives in a common framework. The result is a generalization of [Gaussian processes](https://paperswithcode.com/method/gaussian-process) and Student-t processes that exploits EBMs for greater flexibility.

Energy Based Process

Energy-Based Processes for Exchangeable Data

Dense Connections

**Self-Attention Network** (**SANet**) proposes two variations of self-attention used for image recognition: 1) pairwise self-attention which generalizes standard [dot-product attention](https://paperswithcode.com/method/dot-product-attention) and is fundamentally a set operator, and 2) patchwise self-attention which is strictly more powerful than [convolution](https://paperswithcode.com/method/convolution).

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