AI Glossary Term

What does “Neural Network” mean?

Definition

A layered computational model inspired by biological neurons and synapses.

Browse the full AI Glossary Explore all free AI guides

How Neural Network works

Example

A small network for reading handwritten digits takes 784 pixel values, passes them through hidden layers of weighted sums, and outputs ten scores, one for each digit. Training tunes the weights until the right score is highest.

Why it matters

Neural networks are the foundation of modern deep learning, including language models and image generators.

Common questions

Are neural networks like brains?

Only loosely inspired by them. Artificial networks are mathematical functions and differ greatly from biological neurons.

What does an artificial neuron do?

It takes inputs, multiplies each by a weight, adds them up, and passes the result through an activation function.

How big are they?

From a few hundred parameters in tiny examples to hundreds of billions in the largest language models.

Convolutional Neural Network (CNN)A neural architecture optimized for processing grid-like data such as images.WeightA learned numeric value that scales signals passing through a neural network.BackpropagationThe core training algorithm that updates model weights by propagating prediction errors backward through the network.Deep LearningA subset of machine learning that uses many-layer neural networks for representation learning.GAN (Generative Adversarial Network)A generative setup where a generator and discriminator train against each other.PruningRemoving less important model weights or neurons to reduce size and compute.

Learn more in our free guides

Neural Networks Hard Parameter Sharing in Multi-Task Networks Bidirectional Recurrent Networks Squeeze-and-Excitation Networks

Test yourself

Neural Networks Quiz Hard Parameter Sharing in Multi-Task Networks Quiz Bidirectional Recurrent Networks Quiz