Can machine-learning models overcome biased datasets?

Researchers have applied the tools of neuroscience to study when and how an artificial neural network can overcome bias in a dataset. They found that data diversity, not dataset size, is key and that the emergence of certain types of neurons during training plays a major role in how well a neural network is able to overcome dataset bias.

Source : https://www.sciencedaily.com/releases/2022/02/220221115403.htm

Date : February 21, 2022 at 07:31PM

Tag(s) : Médias spécialisés