Deep learning is just another way of doing statistics.
-it makes strong assumption
-you have large amounts of data
-classifying into categories.
-test data aren't far from training examples
@GaryMarcus #ttiintelligencepic.twitter.com/7xcFRNE3NI
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
If you imagine or perceive a cow, you will have to represent a superpositional state that approximates probabilities. But when you access that representation for reasoning or prediction, you will get a collapsed version (because a probability cloud shaped cow is very unlikely).
It's impossible to represent every possible cow in memory seen from different angles because the number is infinite. We only maintain high level bits of what a cow looks like. And yet we can recognize a cow image mixed with > 90% noise. And when we do, we are 100% certain.
We can represent the angle as indeterminate. If you need to reason about the cow, you generate it with a definite angle but put low confidence on it, so the angle is not clamped down and can be regenerated if the constraints change.
Twitter may be over capacity or experiencing a momentary hiccup. Try again or visit Twitter Status for more information.