[komaromy]

> Computers understand things as well as us, perhaps better.

If this was limited to chess, I would unquestionably agree.

If it was limited to image recognition, I would tentatively agree, although things like [0] make me cautious (admittedly, that was from March, and I'm not familiar with progress since then).

However, the author seems to be generalizing beyond those two domains, to the limits of human understanding. That seems like a couple-orders-of-magnitude leap too far to me. For example, I don't know of any autonomous system capable of understanding a short novel with simple language and writing a one-page summary of it, as might be expected of a human ten-year-old.

[0] https://twitter.com/Meaningness/status/846478348947668992

[bitL]

To what extent those universal perturbations are causing problems due to insufficient image augmentation? Or due to deficient optimizer used while training CNNs (all optimizers are just heuristics with nasty failure cases)? Could we train a GAN-like DNN on those perturbations to make their effect disappear?

[amelius]

Perhaps your reference [0] would work on the human brain too, if only we could know all the weights assigned to all neurons/axons of the given human this should apply to :)

[statusgraph]

Interestingly, you can treat the NN as a black box (ie, not look at individual weights or even the architecture) and still derive adversarial cases:

https://arxiv.org/abs/1602.02697

[amelius]

Interesting. Would that work on humans too?

[komaromy]

Could be! We'll need a volunteer comfortable with having their neuronal weights experimented on.

[bitL]

You are forgetting local protein-based computations observed in biological neurons we have no clue about...