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
Because we have a long tradition of getting it wrong when we hand implement them. Because it doesn't have to be random - we can learn across generation, eg epigenetic. Because we can be more efficient than nature. And because simulating billions of lives lived isn't out of reach.
you are overcorrecting on the prior history, the same way people who dismissed DL in 2009 were....
also simulating even *one* human brain is currently out of reach. possibly for a long time.
“No, I'm not interested in developing a powerful brain. All I'm after is just a mediocre brain, something like the President of the American Telephone and Telegraph Company.” — Alan Turing I’ll leave it to the reader to offer a contemporary instance of the subject brain.
I don't mean to imply that having no innate prior is the only way or even the best way. I am just arguing that it's not a completely crazy idea. CNNs are a good example of priors and they served us well.
They have and they haven't. My view is that we have pushed them pretty hard and they still have *exactly* the same problems I pointed out seven years ago, when #deeplearning first became popular [ https://www.newyorker.com/news/news-desk/is-deep-learning-a-revolution-in-artificial-intelligence …]:pic.twitter.com/SZAvaWu199
Twitter may be over capacity or experiencing a momentary hiccup. Try again or visit Twitter Status for more information.
