Loading slide
The field didn't debate what had happened. It just moved.
Within a year, deep learning entries dominated ImageNet. The hand-engineered approaches that had been the standard for decades vanished from the competition, and researchers who had spent careers refining them started retraining as deep learning researchers. Not a gradual shift. A pivot.
Error rates kept falling, year after year, until they dropped below what humans could manage on the same images.
And the techniques didn't stay in image recognition. Speech recognition. Natural language processing. Drug discovery. Medical imaging. Within eighteen months of AlexNet, every major AI lab had reorganized around deep learning.