A computing system loosely inspired by biological brains, made of layers of interconnected "neurons" (mathematical functions) that learn patterns from data. Information flows through layers, getting progressively transformed until the network produces an output. Every modern AI model is a neural network of some kind.
Why it matters
Neural networks are the "how" behind all of AI. Understanding that they're math (not magic, not brains) helps demystify what AI can and can't do. They're pattern matchers — extraordinarily powerful ones, but pattern matchers nonetheless.