AI Blog

AI Blog

by Michele Laurelli

Input Layer

/ˈɪnpʊt ˈleɪər/
Architecture
Definition

The first layer of a neural network that receives raw input data.

The input layer has one neuron per input feature. It doesn't perform computation, just passes data to the first hidden layer. Its size is determined by input data dimensions.

Examples

1

784 neurons for 28x28 images

2

Input shape specification

3

Data entry point

Michele Laurelli - AI Research & Engineering