Efficient Training For Artificial Intelligence

Víctor López-Pastor and Florian Marquardt, two scientists at the Max Planck Institute for the Science of Light in Erlangen, Germany, have presented a method by which artificial intelligence could be trained much more efficiently. This approach relies on physical processes instead of the digital artificial neural networks currently used, which could reduce the energy consumption of computers and AI-applications. Neuromorphic computing is a concept of how computers could process data in the future, which is modelled on the brain’s way of working, but digital computers serve as the hardware.