Beginner · Neural Networks

Input Layer

Visual diagram · (in preparation) · Math · (in preparation) · Worked example · 3 difficulty levels.

TL;DR. The first layer of a neural network, where raw features enter the model.

Technical Definition

The first layer of a neural network, where raw features enter the model.

How it works

The input layer's size matches the dimensionality of the data — 784 for a flattened 28×28 image, the embedding dimension for text tokens, three channels for an RGB pixel. It performs no computation itself; it just defines the shape of the data flowing in.

Related Concepts

• Layer — A group of neurons that perform the same kind of transformation in parallel.
• Hidden Layer — Any layer in a neural network that is neither the input nor the output.
• Output Layer — The final layer of a neural network that produces the prediction.