How Do Neural Networks Work?

What is a Neural Network?

A neural network is a computing system loosely inspired by the brain. It's made of layers of connected "neurons" that learn to map inputs to outputs by adjusting weights.

The Structure

Input Layer → Hidden Layer(s) → Output Layer

[pixels] → [neurons] → [neurons] → [cat / dog]

How a Neuron Works

output = activation( (input1 × weight1) +
                     (input2 × weight2) + bias )

How They Learn (Training)

1. Forward pass — data flows through, produces a prediction.
2. Loss — measure how wrong the prediction is.
3. Backpropagation — adjust weights to reduce error.
4. Repeat millions of times until accurate.

Activation Functions

Function	Use
ReLU	Hidden layers (default)
Sigmoid	Binary output
Softmax	Multi-class output

FAQs

What is a "deep" network?

One with many hidden layers — that's "deep learning." More in our AI guides.

What is backpropagation?

The algorithm that calculates how to adjust each weight to reduce error.