# What is Fully Connected Layer? Definition & Technical Mechanics

> **Source:** [SPIDITS AI AI Glossary](https://spidits.com/ai-glossary)  
> **Category:** Neural Architectures  
> **Canonical Citation:** [https://spidits.com/ai-glossary/fully-connected-layer](https://spidits.com/ai-glossary/fully-connected-layer)

## Definition
A Fully Connected Layer (Dense Layer) is a layer in an artificial neural network where every neuron is connected to all neurons in the previous layer, mapping linear combinations of inputs to outputs.

## Architectural Mechanics & Deep Dive
A fully connected layer (or dense layer) is a traditional neural network layer where every neuron is connected to every activation neuron in the preceding layer. Each connection has an associated weight. Fully connected layers are typically used at the end of convolutional neural networks to aggregate extracted features and output final classification probabilities.

## Industry Applications & Real-World Use Cases
Deep learning classification output layers, MLPs, and traditional network blocks.

## Frequently Asked Questions

### What operation occurs in a fully connected layer?
Matrix multiplication of the inputs and weights plus a bias vector, passed to an activation function: `y = f(W*x + b)`.

### Why did CNNs replace fully connected layers for image features?
Fully connected layers require too many parameters for high-res images, whereas CNNs share parameters to reduce memory.

## Related Terminology
- [neural-network](https://spidits.com/ai-glossary/neural-network)
- [cnn](https://spidits.com/ai-glossary/cnn)
- [activation-function](https://spidits.com/ai-glossary/activation-function)

---
*From the SPIDITS AI Knowledge Base (336+ terms indexed). Explore full technical definitions: [https://spidits.com/ai-glossary](https://spidits.com/ai-glossary)*