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
This new interface has two facets: data collection & annotation processes on one hand, and loss function engineering on the other hand -- a way to specify the abstractions you want to encode, and what you need to do with them.
What everyone is so focused on -- the big piles of nonlinear transforms trained with gradient descent -- is just an implementation detail in the background.
It starts and ends with data, that's why your machine learning interface should be forgiving and provide a lot of room for user feedback.
Thank you for this excellent clarification of modern tool use! We’ve abstracted the tool into the metaphysical domain, yet as a tool it will be used exactly as we intuit. Which is to say... possibilities are in the [mind’s eye] of the beholder.
well, the fact that neural networks are simulated brain tissue is a very very important aspect too
I don't like all those people saying that neural networks are "just another machine learning technique". No! the fact that it is simulated brain tissue is very very significant
Twitter may be over capacity or experiencing a momentary hiccup. Try again or visit Twitter Status for more information.
