MIT researchers develop AI system that can visually imagine scenarios
Q. MIT scientists have developed a new AI system which can take still images and do what?- Published on 12 Dec 16a. Generate short videos to stimulate what happens next
b. Mimics visual imagining capacity of humans
c. Both of the above
d. Neither of the above
ANSWER: Both of the above
MIT researchers have developed a new artificial intelligence system that can take still images and generate short videos to simulate what happens next, similar to how humans can visually imagine how a scene will evolve.
- Humans intuitively understand how the world works.
- Objects in a still image could move and interact in a multitude of different ways, making it very hard for machines to accomplish this feat.
- The new deep-learning system is able to trick humans 20 per cent of the time when compared to real footage.
- Scientists pitted two neural networks against each other, with one attempting to distinguish real videos from machine-generated ones, and the other making an effort to create videos that were realistic enough to trick the first system.
- When the researchers asked workers on Amazon's Mechanical Turk crowd-sourcing platform to pick which videos were real, the users picked the machine-generated videos over genuine ones 20 per cent of the time.
- The approach could eventually help robots and self-driving cars navigate dynamic environments and interact with humans, or let Facebook automatically tag videos with labels describing what is happening, researchers said.
