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
Whether an AI that plays StarCraft, DotA, or Overwatch succeeds or fails against top players, we'd have learned nothing from the outcome. Wins -- congrats, you've trained on enough data. Fails -- go back, train on 10x more games, add some bells & whistles to your setup, succeed.
Any problem can be treated as a pattern recognition problem if your training data covers a sufficiently dense sampling of the problem space. What's interesting is what happens when your training data is a sparse sampling of the space -- to extrapolate, you will need intelligence.
Sometimes, it's not about the outcome, it's about what you can learn from the process.
I'd rather say "to extrapolate, the system needs intelligence and use it to perform its own sampling" aka focusing; self-supervision; self-directed trial-and-error. Or if you insist on static training data, I'd say you only need to provide an adequate model of the world.
That's what I believe as well. The less data you use the more remarkable the result. It's also why I believe consciousness is tied to intelligence in some way, because that inner voice is maybe the best extrapolator in the known universe.
by extrapolation, do you mean truly generalizing outside the range of the training data, or just the ability to generalize to sparse regions of the training data?
This is the best statement I have seen to-day. However, generally, when the sampling space is actual and real, it is not ergodic (i.e. context dependent) and expanding it is not sufficient.
Twitter may be over capacity or experiencing a momentary hiccup. Try again or visit Twitter Status for more information.
