Når et meget ungt barn kigger på billeder, kan hun identificere simple elementer: "Kat", "bog", "stol". Nu er computere ved at være så smarte at de kan gøre det også. Hvad er så det næste? I en spændende talk, computersyns ekspert Fei-Fei Li beskriver status - herunder en database med 15 millioner fotos som hendes team har samlet for at "lære" computere at forstå billeder - og stadigvæk mangler der meget.

Hvordan vi lærer computere at forstå billeder

Computers are rapidly learning to interpret images, a feat that took nature over 500 million years to evolve in the human brain. By building a database of 15 million labeled photos, researchers have allowed algorithms to make sense of the visual world, much like a child learning from experience. Today, machines can identify objects in photos and even generate human-like sentences about what they see. This progress promises smarter tools and new forms of human–machine collaboration, but true visual understanding is still unfolding.