Thread Rating:
  • 0 Vote(s) - 0 Average
  • 1
  • 2
  • 3
  • 4
  • 5

Helping machines perceive some laws of physics

#1
C C Offline
https://news.mit.edu/2019/adept-ai-machi...ysics-1202

INTRO: Humans have an early understanding of the laws of physical reality. Infants, for instance, hold expectations for how objects should move and interact with each other, and will show surprise when they do something unexpected, such as disappearing in a sleight-of-hand magic trick.

Now MIT researchers have designed a model that demonstrates an understanding of some basic “intuitive physics” about how objects should behave. The model could be used to help build smarter artificial intelligence and, in turn, provide information to help scientists understand infant cognition.

The model, called ADEPT, observes objects moving around a scene and makes predictions about how the objects should behave, based on their underlying physics. While tracking the objects, the model outputs a signal at each video frame that correlates to a level of “surprise” — the bigger the signal, the greater the surprise. If an object ever dramatically mismatches the model’s predictions — by, say, vanishing or teleporting across a scene — its surprise levels will spike.

In response to videos showing objects moving in physically plausible and implausible ways, the model registered levels of surprise that matched levels reported by humans who had watched the same videos.

“By the time infants are 3 months old, they have some notion that objects don’t wink in and out of existence, and can’t move through each other or teleport,” says first author Kevin A. Smith, a research scientist in the Department of Brain and Cognitive Sciences (BCS) and a member of the Center for Brains, Minds, and Machines (CBMM). “We wanted to capture and formalize that knowledge to build infant cognition into artificial-intelligence agents. We’re now getting near human-like in the way models can pick apart basic implausible or plausible scenes.” (MORE)
Reply


Possibly Related Threads…
Thread Author Replies Views Last Post
  Research Perspective paper explores the debate over sentient machines C C 1 52 Feb 3, 2024 08:02 PM
Last Post: Magical Realist
  Article Training machines to learn more like humans do C C 0 68 May 9, 2023 11:27 PM
Last Post: C C
  Artificial Intelligence that can discover hidden physical laws in various data C C 0 60 Dec 11, 2021 05:08 AM
Last Post: C C
  It takes a lot of energy for machines to learn Leigha 4 294 Jan 15, 2021 02:06 PM
Last Post: confused2
  Intelligence without causal theory, laws, & other concepts for understanding... C C 0 118 Aug 16, 2020 11:06 PM
Last Post: C C
  Intelligent machines might want to become biological again C C 0 345 Jul 6, 2017 12:12 AM
Last Post: C C
  How computer games satisfy basic needs + Machines learning to disambiguate people C C 1 393 Jan 14, 2017 03:02 PM
Last Post: Ben the Donkey
  How researchers are teaching computers the laws of physics C C 0 931 Jan 7, 2016 10:41 AM
Last Post: C C
  7 unexpected outcomes of the singularity + When machines learn like humans: The end? C C 1 734 Dec 15, 2015 11:38 PM
Last Post: Magical Realist
  Physical nature of computers may reveal deep truths + How machines learn and you win C C 0 802 Dec 6, 2015 10:06 PM
Last Post: C C



Users browsing this thread: 1 Guest(s)