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
Deep learning is capable of performing reasoning tasks, in the sense that it's pattern recognition engine, and any task (including ones we would categorize as involving reasoning) can be cast as pattern recognition, given a sufficient dense sampling of the input/output space.https://twitter.com/gdb/status/1116381180079656960 …
It's also technically possible to train deep learning models to perform specific symbolic tasks (say, arithmetic, sorting...) using *few* data points, if you hard-code that task in the architecture space (replacing learning with a prior)...
Neither "train on a dense sampling of the data" nor "practically hard-code a solution template and then tune a few parameters using SGD" are particularly good options.
"In general, anything that requires reasoning—like programming, or applying the scientific method—long-term planning, and algorithmic-like data manipulation, is out of reach for deep learning models, no matter how much data you throw at them." — https://blog.keras.io/the-limitations-of-deep-learning.html …
To pattern or not to pattern, that is the question.
In which terms then we can say that #prolog did not succeeded in understanding and reasoning given the fact that the knowledge was built a prior and all the patterns were potentially known?
From a practical perspective, that's correct. However, naming "reasoning" what happens inside a neural net is an anthropomorphization. Reasoning is by definition something which requires logic and sensible thinking.
And what is the specific cell in your brain that performs these ?
Twitter may be over capacity or experiencing a momentary hiccup. Try again or visit Twitter Status for more information.
