Neural network

An artificial neural network is a computing model inspired, in a very simplified way, by how the brain’s neurons connect. It is made of nodes ("neurons") organized in layers: each connection has a weight, and during training those weights are gradually adjusted so the network gives the right answer. Once trained, it processes new data by passing it layer by layer until it produces a result, such as classifying an image or predicting the next word. When the network has many layers, we call it deep learning ✕ Deep learning is a type of machine learning that uses neural networks with many layers. It is what lies behind the recent leaps in AI. More in the glossary → . The comparison with the brain is only a metaphor: the mathematical principles differ from real biology. It is the central component of most current AI ✕ Artificial intelligence is a computer system’s ability to perform tasks we associate with human intelligence, such as understanding language, recognizing images or making decisions. More in the glossary → systems.