**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.

**PP-YOLOv2** is an object detector that extends upon [PP-YOLO](https://www.paperswithcode.com/method/pp-yolo) with several refinements:

- A [Path Aggregation Network](https://paperswithcode.com/method/pafpn) is included for the FPN to compose bottom-up paths.
- [Mish Activation functions](https://paperswithcode.com/method/mish) are used.
- The input size is expanded.
- An IoU aware branch is calculated with a soft label format.

PP-YOLOv2

PP-YOLOv2: A Practical Object Detector

Energy Based Process

Energy-Based Processes for Exchangeable Data

**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

Source	Energy-Based Processes for Exchangeable Data
Year	2000
Data Source	CC BY-SA - https://paperswithcode.com