Loading slide

ImageNet and the Turning Point

  1. 01ImageNet and the Turning Point
  2. 02Fei-Fei Li and ImageNet
  3. 03The traditional approach
  4. 04AlexNet
  5. 05What it felt like
  6. 06What made it work
  7. 07How it taught itself
  8. 08Take a breath
  9. 09What did it actually learn?
  10. 10The field responds
  11. 11Why this was a hinge
  12. 12Memory card
  13. 13Reinforce your understanding
  14. 14Question: Data vs. algorithm
  15. 15Question: Hand-engineered vs. learned features
  16. 16Question: What does a turning point feel like from inside?
  17. 17Quiz: answer
  18. 18What you now know
  19. 19The machine could now see. The next question was whether it could read.
  20. 20Want to go deeper?
10 / 19
BackNext

The field responds

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.

Citations(2)↓
  1. 1. ieeexplore.ieee.org
  2. 2. arxiv.org