Neural Network (NN)
A neural network is a computer system loosely inspired by the way brain cells connect. It is built from layers of simple units, called nodes, that pass signals to one another. By adjusting the strength of those connections while learning from examples, the network gradually gets better at a task, whether that is recognising a face, translating a sentence, or predicting the next word. Almost all modern AI is built on neural networks of one kind or another.
Picture a very large team of people passing notes. Each person reads the notes they receive, does a tiny calculation, and passes a new note onward. No single person understands the whole problem, but the team as a whole can produce a sensible answer. A neural network works in much the same way: each node handles a small piece of the calculation, and the answer emerges from all of them working together.
The clever part is how a neural network learns. When it makes a mistake, it nudges the strength of its internal connections a little, so that next time it is slightly more likely to get the answer right. Repeat this across millions of examples and the network slowly tunes itself into something genuinely useful. Nobody writes explicit rules for it; it works out the patterns on its own.
This is why neural networks matter so much. Traditional software needs a human to spell out every rule, which is hopeless for messy tasks like understanding speech or spotting a tumour on a scan. A neural network learns the rules from data instead, which is what makes today’s AI possible. When you read about an AI model with “billions of parameters”, those parameters are the connection strengths inside a neural network.