What is a neural network?
A neural network is a machine learning model made of layers of simple connected units, loosely inspired by the brain. Each connection has a weight; training adjusts those weights so that the network turns inputs, like pixels or words, into useful outputs, like labels or the next word.
How does a neural network work?
Data flows in at one end, gets multiplied by weights and passed through each layer, and comes out as a prediction. Training compares the prediction with the right answer and nudges every weight in the direction that reduces the error (gradient descent).
Why does a neural network matter?
Neural networks are the building blocks of deep learning and every large language model. Understanding them makes the rest of AI make sense.
An example
Example: A neural network that reads handwritten digits on a cheque learns to turn a grid of pixels into the right number.
Related terms
Learn it properly
A neural network is covered in AI Engineer, with short lessons, practice questions and instant feedback.