Viet-Anh on Software Logo

What is: Dense Connections?

Year2000
Data SourceCC BY-SA - https://paperswithcode.com

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_inputsn_outputsn\_{\text{inputs}}*n\_{\text{outputs}} parameters, which can lead to a lot of parameters for a sizeable network.

h_l=g(WTh_l1)h\_{l} = g\left(\textbf{W}^{T}h\_{l-1}\right)

where gg is an activation function.

Image Source: Deep Learning by Goodfellow, Bengio and Courville