AI engineering glossary · Deep learning core
What is fan-in and fan-out?
Fan-in and fan-out: The number of inputs feeding into a neuron or layer (fan-in) and the number of outputs it sends signals to (fan-out). Initialisation formulas use these counts to scale the starting weights so that signals keep a sensible size.
Fan-in and fan-out: an example
A dense layer from 300 units to 100 units has fan-in 300 and fan-out 100.
Related terms
More Deep learning core terms
- Feedforward neural network
- Flat minima
- Focal loss
- Forward pass
- Fully connected layer
- Gated linear unit
- Gating mechanism
- GELU
Where you learn it
Fan-in and fan-out is part of the AI Engineering Program, which teaches it with notes, a hands-on lab and an exam. The first lesson is free.