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
A more interesting theoretical distinction between "supervised" and "unsupervised" learning could be: 1. Forms of learning driven by an explicit, known objective vs. 2. Forms of learning driven by open-ended discovery and ever-shifting objectives elected by the system itself
All current "unsupervised learning" fits in the first category (for instance, PCA uses data reconstruction as its objective). The second category is basically exclusive to biological systems at this time. It will probably be a while until AI meaningfully encroaches on it.
It won’t until we nudge it into self-preservation as its main overarching goal.
Doesn't reinforcement learning fit in this category?
If you are able to develop RL algorithms without defining reward functions explicitly (or a notion of them with a priori model knowledge), then there is no difference.
First
Why not call it self supervised learning like @ylecun ?
I guess it depends what you mean by “meaningfully” but there’s a whole area of study and some great research into Intrinsic Motivation as an umbrella term for things like exploration, curiosity and play. That fits the second category doesn’t it?
I think biological systems also have objectives: human has objective of maximizing happiness, animals have objective to survive. These are not as well defined as ML tasks as of now though.
I think you're erroring in your premise of objectives. There's no evidence that you could conclude humans have an objective or maximizing happiness (ignoring the amorphous definition of happy). It may be a fleeting ambition, but certainly not a grand ambition or goal.
Not convinced, in that I am pretty sure most of the biological ones are the same except you don’t know what the invariants are, yet. As we unravel their behaviours, we might find an objective we can ascribe, just as we do with PCA.
Twitter may be over capacity or experiencing a momentary hiccup. Try again or visit Twitter Status for more information.
