In a Nature Communications study, researchers from China have developed an error-aware probabilistic update (EaPU) method ...

Researchers have developed an algorithm to train an analog neural network just as accurately as a digital one, enabling the development of more efficient alternatives to power-hungry deep learning ...

The simplified approach makes it easier to see how neural networks produce the outputs they do. A tweak to the way artificial neurons work in neural networks could make AIs easier to decipher.