Artificial neural networks made from memristors for brain-inspired computing
While reading these lines, your brain is efficiently performing image recognition to identify letters and words, matching it with your learned vocabulary to understand the content. Modern computer chips operate in a similar manner, providing a platform for running what are called artificial neural networks.
These are virtual networks made of artificial neurons and synapses, which are trained to process information for specific tasks such as facial recognition to unlock smartphone displays or tumor detection from brain scans. However, compared to the brain, artificial neural networks run on conventional computers are extremely slow and consume large amounts of energy.
To read more go to Advanced Science News.
Reference: Jan L. Rieck, Beatriz Noheda, et al., Ferroelastic domain walls in BiFeO3 as memristive networks , Advanced Intelligent Systems (2022), DOI: 10.1002/aisy.202200292
| Last modified: | 20 December 2022 09.58 a.m. |
More news
-
28 March 2023
A leap of faith: from research to enterprise
Having ideas, experimenting and trying things out, wanting to change society. For many researchers, all of this is day-to-day business. But what if you want to take your idea to market? This is a step that often does not come naturally to...
-
14 February 2023
Lift to the inclusive workplace
There is plenty of work, and yet people with a disability are still often sidelined. One plus one is two, or so you’d think: this is the perfect time to help this group of workers find a job. The intention is there, also within the University, but...
-
15 December 2022
Groningen contributes to major research initiative into energy-efficient information technology
The Dutch science funding agency NWO recently awarded a large research project into new concepts for energy-efficient information technology of no less than ten million euros