The biggest problem in AI? Machines have no common sense. Great video by @GaryMarcus.
#ArtificialIntelligence #MachineLearninghttps://bigthink.com/videos/how-smart-are-robots-ai …
-
Commonsense is just the amortized inference that humans have accumulated in their life. When automation like AlphaGo makes an unexpected move (see move 37) it isn't a common sense move because we have no access to reasoning behind it. But most of AlphaGo's moves are commonsense.
not much in common there with the sorts of commonsense reasoning about space, time, and causality that Davis and I emphasize, nor would these things in any obvious way be helpful for the domains in which we stress the need (reading, robotics, safety etc).
-
-
I agree that space, time and causality are different domains from the game of Go. However, fundamentally, our intuitive understanding of space, time and causality are due to the amortized inference that evolution has developed for us over the eons. That's the breakthrough of DL.
-
this is totally confused. major emphasis in deep learning has been in trying to learn things bottom up from data, whereas nativists stress power of what evolution has done, to build strong starting points - that are often in the deep learning community considered to be "cheating"
- 2 more replies
New conversation -
Loading seems to be taking a while.
Twitter may be over capacity or experiencing a momentary hiccup. Try again or visit Twitter Status for more information.