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
@GaryMarcus "search a different part of model space" is not a testable proposal, nor your whole book from 2001 is. I wanted to hear what that different part is, in equations or pseudo code.
ps 2001 book proposed many specific problems ranging from generalizing low frequency default morphology to acquiring universally quantified one to one mappings to tracking identity and properties of individuals over time. community really has not engaged in any of these.
Researchers rarely engage with general audience non-fiction. If your goal is community engagement, try publishing where they publish. Paying money and sifting through hundreds of pages is a big ask.
Steve, tons of us at DeepMind have read The Algebraic Mind. I see it on people's desks all the time. It's more of a long review article than a popsci book. This is why the usual response to Gary's critiques is "we know, you've been repeating the same thing forever."
This is a red herring. Problem proposals are not solution proposals.
agreed. but we need consensus about what the problems are before we can find solutions not appeals to ever bigger data sets when Bengio recently acknowledged core of what I said about generalization in 2001 it was first time I saw ML leadership really engage core problem.
An algorithm can't look at pictures of bridges and "know" how best to engineer them because the data is superficial. How do you test the inability to extrapolate outside of the given data? They know this because "if given enough data" is their mantra.
Can you give an example of this concept ?
f(x) = x. each input x has a unique output standard backprop net representing inputs as binary numbers trained on a subset of even numbers can generalize (imperfectly) to other even numbers but not odd numbers. patching specific case is easy; general solution is hard.
Twitter may be over capacity or experiencing a momentary hiccup. Try again or visit Twitter Status for more information.
