News for hackers. Stuff that matters.
Re:When not to use deep learning by shadowmint on Sunday July 09, 2017 @10:54PM (#14733070)
Don't just down vote this guys, that doesn't help.

No, your naive understanding is not correct.

'Deep learning', and by that I mean a neural network, works at a super high level by generalising some input (say X) into some related output (lets say, Y).

It's not just random choice; it's like defining a programming function:

    foo(x) -> y { ... }
Where the '...' is implemented by a set of statistical weights and training data and so on.

...but ultimately, you raise a valid point.

Training models is incredibly time consuming, and incorporating 'corrections' as new training data is extremely non trivial.

It's one of the issues with deep learning.

I would even go as far as to say, 'You need to regularly update your training data with new examples and counter examples' as a 'when not to use deep learning'.

Re:When not to use deep learning by aklemm on Monday July 10, 2017 @10:59AM (#14736503)
There was no mention of random choice (was there?) and the naive description seems to line up with your description.