Neural network
The structure most modern AI is built on, loosely modelled on how brain cells connect. It is made of artificial neurons: tiny functions that take numbers in, weigh them, and pass a result to the next one along. Arranged in layers, millions of them, what the system knows is held in the strength of the connections between them rather than in any rule someone wrote.
That is the difference from ordinary software. A normal program does what it was told. A neural network is shown thousands of examples, adjusts its connections every time it gets one wrong, and ends up able to recognise a face, price a booking or finish a sentence without anyone ever having specified how. Stack enough layers and you get deep learning.
Attention Is All You Need – why transformers changed artificial intelligence
…had held back natural language processing systems for more than two decades. Classic neural networks did well on tasks where all the data was available at once — image analysis, for example. Language works differently. The meaning of a sentence depends on word order, and…
AI doesn’t think. AI computes.
…become computable. And when relationships get too tangled for any ready-made rule, neural networks take over, processing information in layers where each level's analysis feeds the next. That cascade is all "deep learning" means. Hand it examples pre-labeled by humans…