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
Given infinite data, you can solve arbitrarily complex problems with a "dumb" model (such as a densely-connected neural network). However, when it comes to difficult real-world problems like self-driving, "lots of data" is very different from "infinite data". The long tail is fathttps://twitter.com/fchollet/status/1032444572306042880 …
There is no realistic amount of data that covers "everything you can encounter" in the real world. That's what intelligence is for: to be able to handle the real world despite having only seen a very small sample of what may happen. Intelligence is extreme generalization.
Can you expound a bit more what you mean by infinite data in terms of "signal" vs "noise"?
Not sure this is really helpful.
Consciousness may well be the most complex thing we do.
New “yo mama” joke: Yo mama is so dumb, she learns using a densely-connected neural network. On a more serious note, the day NNs are described as dumb came sooner than I expected.
Just recently learnt about neural networks and find it amusing when you called dense NNs, dumb.
Another form of PDF estimation
On what evidence is this qualitative chart based. Do you have any refs that support this hypothesis (regarding self-driving cars)?
What a shame it is that one neural network can’t sit down beside another with a foot on a brake in the passenger seat, and encouraging advice
A population of agents that can teach each other, can distill a billion experiences into a tiny number of experiences for the next generation, can know how and where to probe for understanding of the learner, that population could develop a theory of engineering
Twitter may be over capacity or experiencing a momentary hiccup. Try again or visit Twitter Status for more information.
