News for hackers. Stuff that matters.

A comment on The Limitations of Deep Learning. Parent comment

Re:The Limitations of Deep Learning by eli_gottlieb on Monday July 17, 2017 @04:29PM (#14792031)
>If you take a purely input-output view of the world (which by the way, even classical Physics does), every problem _is_ curve fitting in a sufficiently high dimensional space.

Not all spaces are Euclidean, and "purely input-output" still contains a lot of room for counterfactuals that ML models fail to capture.

[ Parent | on HN ]
Re:The Limitations of Deep Learning by nerdponx on Monday July 17, 2017 @10:05PM (#14793832)
What do you mean by counterfactuals? NNs are function approximation algorithms, in any geometry. No ifs ands or buts about it.
[ Parent | on HN ]
Re:The Limitations of Deep Learning by eli_gottlieb on Monday July 17, 2017 @10:33PM (#14793914)
Oh, I agree that neural networks are function approximators with respect to some geometry. When I say "counterfactuals", I'm talking about typical Bayes-net style counterfactuals, but as also used in cognitive psychology. We know that human minds evaluate counterfactual statements in order to test and infer causal structure. We thus know that neural networks are insufficient for "real" cognition.
[ Parent | on HN ]