AI Blog

AI Blog

by Michele Laurelli

Fully Connected Layer

/ˈfʊli kəˈnɛktɪd ˈleɪər/
Architecture
Definition

A neural network layer where every neuron is connected to every neuron in the previous and next layers.

Also called dense layers, they perform classification or regression after feature extraction. Each connection has a learnable weight. Common at the end of CNNs for final decision making.

Examples

1

Classification layer in CNNs

2

MLP hidden layers

3

Output layer

Michele Laurelli - AI Research & Engineering