From: Marius Amado-Alves <amado.alves@gmail.com>
Subject: Re: requiring Ada(2020?) in self-driving autonomous automobiles
Date: Mon, 26 Nov 2018 03:44:54 -0800 (PST)
Date: 2018-11-26T03:44:54-08:00 [thread overview]
Message-ID: <94e66f34-494b-4aa3-9298-5cc2ca073b26@googlegroups.com> (raw)
In-Reply-To: <p9vfns$12a4$1@gioia.aioe.org>
> Humans can explain things, forget things, do erratic things time to
> time. This is how it works with us based on our worldview, moral,
> ethics, instincts etc. How would it work with an NN? Well, most likely
> it will not. (Dmitry A. Kazakov)
Theoretically it is possible with deep networks of the right architecture. Problem is this right architecture is very hard to find, requires a "deep" understanding of the theory, and the very few people at this level like Ng, Hinton, are now "directors" of something, don't create architectures any more. That is now done in a typewriting monkey way by the new machine learning practioners, turning knobs by instinct at best. So, yeah, it will not happen soon.
next prev parent reply other threads:[~2018-11-26 11:44 UTC|newest]
Thread overview: 10+ messages / expand[flat|nested] mbox.gz Atom feed top
2018-03-28 13:26 requiring Ada(2020?) in self-driving autonomous automobiles Dan'l Miller
2018-03-28 14:24 ` Dan'l Miller
2018-03-28 14:26 ` Dan'l Miller
2018-03-28 21:38 ` Bojan Bozovic
2018-03-29 3:56 ` Dan'l Miller
2018-03-29 7:21 ` Bojan Bozovic
2018-04-02 21:06 ` Robert I. Eachus
2018-04-03 8:58 ` Dmitry A. Kazakov
2018-11-26 11:44 ` Marius Amado-Alves [this message]
2018-11-26 17:31 ` Dmitry A. Kazakov
replies disabled
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox