You can add location information to your Tweets, such as your city or precise location, from the web and via third-party applications. You always have the option to delete your Tweet location history. Learn more
The difference here is that @Marcus uses a proof by negation while connectionists have proofs by construction. The former is lazier than the latter.
it was hard work discerning a fundamental limit (in 1998) when everyone imagined neural networks were magic, and it’s been even harder work to get people to recognize the importance of that limit. (some do, now; most still don’t; many insult me rather than reckon with it)
"there is really only one viable route from sense to symbols: from the ground up." "The Symbol Grounding problem" 1999 details argument https://arxiv.org/abs/cs/9906002v1 … #deeplearning #ai
The connectionist argument has always been that reasoning will eventually be learned, but to do so, you have to build your way from the ground up. Evolving from the top down doesn't work.
Twitter may be over capacity or experiencing a momentary hiccup. Try again or visit Twitter Status for more information.
