Artificial neural networks: Technologies
Technologies
The technologies that rely on it, and how each one uses it
Relied on by 9- DL Deep learning Deep networks are stacks of layers of artificial neurons whose connection weights are adjusted during training [8].
- LLM Large language models Language models are very large networks of artificial neurons whose weights are set by training on text.
- AIx AI diagnosis from medical images The software is built from layers of artificial neurons that turn pixel values into a finding.
- AV Autonomous driving Perception software uses layered neural networks that learn to recognise objects from examples rather than from written rules.
- BCI Brain-computer interface Decoders built from neural network models turn recorded brain signals into intended words or movements.
- Hmn General-purpose humanoid robots Learned skills come from neural network models that turn sight and instructions into movement.
- Nm Neuromorphic computing Each core models artificial neurons that add up weighted inputs and fire, an idea built as a machine since Rosenblatt's perceptron [4].
- Swm Autonomous drone swarms In principle terms, learned perception and control software is built from layers of artificial neurons.
- AI accelerator chip The work is the layer-by-layer multiply-and-add of artificial neural networks, which the chip's arithmetic units are built for.
as of 2026-11-12
Sources
- Professor’s perceptron paved the way for AI - 60 years too soon Cornell Chronicle, Cornell University (Melanie Lefkowitz), 2019
- Learning representations by back-propagating errors Nature (D. E. Rumelhart, G. E. Hinton and R. J. Williams), via the SAO/NASA Astrophysics Data System, 1986