This is as insane and frightening as it gets. Until now, AI has relied on millions of hours of rigorous machine learning with no ‘intuition’ of its own. While Google recently debunked a sentient AI in their labs, DeepMind, a UK-based AI research lab, claims its Artificial Intelligence can mimic a human baby! Isn’t that cool? Maybe! This AI, dubbed ‘PLATO’ for Physics Learning Through Auto-Encoding and Tracking Objects, learned physics like a toddler.
PLATO was taught to recognise objects and their interactions by DeepMind AI researchers using simulated videos of objects moving as we would expect. To improve PLATO’s performance, they used video training data to show videos of many simple scenes. It employs objects at all stages of processing, including representing visual inputs as a set of objects, reasoning about object interactions, and producing outputs.
According to Piloto, the findings indicate that an object-centric view of the world could provide an AI with a more generalised and adaptable set of abilities. The findings could open up new avenues for AI research and even provide insights into human vision and development. However, PLATO implementation is not externally viable. The findings suggest that visual animations can explain some intuitive physics learning, but not enough to explain what we see in infants.
Humans understand the physical world with ease, but AI models cannot. New research in @NatureHumBehav takes inspiration from dev. psych to build a benchmark for physical understanding. PLATO shows strong results and generalises to new objects: https://t.co/upS32SFRbX 1/2 pic.twitter.com/lzeFIYPpeB
— DeepMind (@DeepMind) July 11, 2022
“In comparison to even very young children, current artificial intelligence systems pale in their understanding of intuitive physics,” the study authors wrote in their paper. “We address this gap between humans and machines here by drawing on developmental psychology.”