Deep learning
Many-layered neural networks learn to recognise images, speech and patterns from data.
Computing and AI · AI and data · No. 290
- Digital age
- Readiness 9 of 9
- Process
An idea only a small group of researchers still backed in the early 2000s now recognises images, transcribes speech and translates text.
Chart: Illustration: Deep learning
Where it comes from
Chart: Map of where it comes from
Rosenblatt showed his perceptron in 1958. Hinton and colleagues made multilayer networks learnable with backpropagation in 1986; by 1998 such networks read bank cheques commercially, and in 2012 Toronto students almost halved the ImageNet error rate.
Three things to know
- Backpropagation, the method that trains layered networks, was set out in a 1986 paper by Rumelhart, Hinton and Williams.
- In 2012 a network trained on two graphics cards almost halved the error rate in the ImageNet image-recognition contest.
- Hopfield and Hinton shared the 2024 Nobel Prize in Physics for work that made machine learning with neural networks possible.
The journey
- 1 DataMillions of labelled examples, such as photos tagged with what they show
- 2 NetworkMany layers of simple artificial neurons joined by adjustable weights
- 3 TrainingBackpropagation nudges every weight to reduce the errors, on GPUs
- 4 ModelThe trained weights now encode patterns found in the data
- 5 UseThe model labels new images, transcribes speech or flags fraud