I think you are misrepresenting of what I wrote. DeepMind chooses to use Reinforcement Learning as the algorithm behind AlphaGo Zero. That's their choice to brand it that way. Predictive Learning is LeCun's branding of unsupervised learning.
.@intuitmachine Your earlier reply to me carelessly confused the difference between self-play (invented by Samuel in 1959), RL (eg Sutton, 1984, a quarter century later), and predictive learning, in the space of a single paragraph. I urge you to up your game and be more careful.https://twitter.com/intuitmachine/status/948963626127364097 …
-
-
-
Besides, you haven't addressed my argument that human brains are intuition machines and not algebraic minds.
#deeplearning#ai How do you respond to that?
End of conversation
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.