Re:Language contains human biases, and so will machines trai...
by nl on Thursday August 25, 2016 @08:32AM
(#12358480)
It's pretty hard to return "rules" for a ML system, especially a non-linear system. Google is currently working systems that use a trillion features - I can't imagine returning some kind of rule list for that.
LIME[1] is a nice start, though.
[1] https://www.oreilly.com/learning/introduction-to-local-inter...
Re:Language contains human biases, and so will machines trai...
by wolfgke on Thursday August 25, 2016 @09:22AM
(#12358760)
Another text about interpreting convolutional neural networks:
http://cs231n.github.io/understanding-cnn/
> Google is currently working systems that use a trillion features - I can't imagine returning some kind of rule list for that.
As I wrote: It would already help if the ML system as a first step returned the derivation with only the rules that were concretely used for a concrete derivation - this list is much shorter and can thus much easier be checked.
I don't believe that problem will ever be completely solvable. But I think the road to go is to make these assumptions always explicit. I.e. when the machine learning system derives a result, program it to additionally return a proof of how it came to this result. And also give a way to let the ML system return a list of all axioms and derivation rules that it has currently learned, so that they can independently be checked how much they are biased and can thus be corrected.