A new study explores deep learning for image-based defect detection during 3D printing, looking to catch bad builds.

Researchers built a photonic synapse that strengthens or erases memory by light color, using a defect to mimic the brain's balanced learning.

The human brain actively keeps "learning" in balance by holding on to what matters and letting go of what does not.

Abstract: Computer vision-based methods for rail defect detection can automatically identify defects on railroad surfaces to ensure transportation safety. However, these methods face challenges, such ...

Abstract: Currently, deep neural networks for industrial defect recognition still face imbalance problems, due to the difficulty in accessing the rare defect samples. To address this problem, existing ...