BasicsEasy read
Neural network
Written by Minh Khang
What is Neural network?
A neural network is a computer model made of many connected nodes in layers, inspired by the way neurons in the brain pass signals.
Each node takes numbers in, multiplies them by a weight and passes them on to the next layer. Training adjusts a huge number of weights until the guesses come out right. A neural network does not "think" like a person; it is very good at finding patterns in data.
Neural network in a shop
The text brain behind ChatGPT, Gemini and Claude is a very large neural network trained on an enormous amount of text.
Keep learning beyond the glossary
Read next
- BasicsDeep learningDeep learning is a branch of machine learning that uses many-layered neural networks, and is good with complex data such as images, voice and text.
- BasicsLarge language model (LLM)A large language model (LLM) is the text brain behind ChatGPT, Gemini and Claude: it predicts the most likely next word, one word at a time.
- BasicsMachine learningMachine learning is a way for machines to work out patterns from many examples, instead of a person writing every rule for them.