[ExI] Neural networks score higher than humans in reading and comprehension test

[Dylan Distasio]

This is the Achilles heel of all the deep learning that I've been exposed
to.  Deep nets are also great at image recognition until an adversarial
attack is injected that will fool a net, but not a human child.  There is
zero comprehension.  The nets are dead behind the eyes.  I believe the
folks attempting to replicate actual biological neuron function (the bulk
of deep learning is not much more than high school math and a gradient
descent function to find a global minima) have the best chance of building
something that actually understands what it is doing.

In the mean time, this will become more and more of a problem as these
systems get embedded in our environment and become open to exploit for
profit:

https://blog.openai.com/adversarial-example-research/

On Tue, Jan 16, 2018 at 1:21 PM, Dave Sill <sparge at gmail.com> wrote:

> *However, challenging the “comprehension” description, Gary Marcus, PhD, a
> Professor of Psychology and Neural Science at NYU, notes in a tweet that
> “the SQUAD test shows that machines can highlight relevant passages in
> text, not that they understand those passages.”*
>
> Yep.
>
> -Dave
>
> On Tue, Jan 16, 2018 at 1:13 PM, John Clark <johnkclark at gmail.com> wrote:
>
>> Microsoft achieved 82,650 on the Stanford University reading and
>> comprehension test, the best human score so far is 82,304.
>>
>> http://www.kurzweilai.net/deep-neural-network-models-score-
>> higher-than-humans-in-reading-and-comprehension-test?utm_
>> source=KurzweilAI+Daily+Newsletter&utm_campaign=c8f5d1
>> 257b-UA-946742-1&utm_medium=email&utm_term=0_6de721fb33-
>> c8f5d1257b-282205341
>>
>> John K Clark
>>
>> _______________________________________________
>> extropy-chat mailing list
>> extropy-chat at lists.extropy.org
>> http://lists.extropy.org/mailman/listinfo.cgi/extropy-chat
>>
>>
>
> _______________________________________________
> extropy-chat mailing list
> extropy-chat at lists.extropy.org
> http://lists.extropy.org/mailman/listinfo.cgi/extropy-chat
>
>
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://lists.extropy.org/pipermail/extropy-chat/attachments/20180116/f5754cc4/attachment.html>