If by “narrow domains” you mean pretty much all financial systems, air traffic control systems, medical systems, gaming systems, social networks, weapons systems, computational physics/chemistry/biology you are probably correct. @IntuitMachine @GaryMarcushttps://twitter.com/intuitmachine/status/1003326617182265344 …
-
Agreed; but I'd also argue that learning is not the exclusive domain of neural networks: depending on your meaning of "learn" one could claim that Bayesian networks or even genetic algorithms learn...
or essentially anything in ML, most of which is not neural nets. yet people often (wrongly) equate ML and deep learning.
-
-
This all depends on what deep learning is exactly. Is it probabilistic as the Bayesian's claim? Is it template matching like SVM? Is it entirely something else? See:https://medium.com/intuitionmachine/the-many-tribes-problem-of-artificial-intelligence-ai-1300faba5b60 …
- 8 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.