3Q: Aleksander Madry on building trustworthy artificial intelligence

From	not@telling.you.invalid (Computer Nerd Kev)
Newsgroups	comp.misc
Subject	3Q: Aleksander Madry on building trustworthy artificial intelligence
Date	2019-01-07 22:09 +0000
Organization	Aioe.org NNTP Server
Message-ID	<q10imu$ujn$1@gioia.aioe.org> (permalink)

Show all headers | View raw

3Q: Aleksander Madry on building trustworthy artificial intelligence
 Kim Martineau, 14th of Dec. 2018
- http://news.mit.edu/2018/mit-3q-aleksander-madry-building-trustworthy-ai-1214

"Machine learning algorithms now underlie much of the software we
 use, helping to personalize our news feeds and finish our thoughts
 before we're done typing. But as artificial intelligence becomes
 further embedded in daily life, expectations have risen. Before
 autonomous systems fully gain our confidence, we need to know they
 are reliable in most situations and can withstand outside
 interference; in engineering terms, that they are robust. We also
 need to understand the reasoning behind their decisions; that they
 are interpretable.

 Aleksander Madry, an associate professor of computer science at
 MIT and a lead faculty member of the Computer Science and
 Artificial Intelligence Lab (CSAIL)'s Trustworthy AI initiative,
 compares AI to a sharp knife, a useful but potentially-hazardous
 tool that society must learn to weild properly. Madry recently
 spoke at MIT's Symposium on Robust, Interpretable AI, an event
 co-sponsored by the MIT Quest for Intelligence and CSAIL, and held
 Nov. 20 in Singleton Auditorium. The symposium was designed to
 showcase new MIT work in the area of building guarantees into AI,
 which has almost become a branch of machine learning in its own
 right. Six faculty members spoke about their research, 40 students
 presented posters, and Madry opened the symposium with a talk the
 aptly titled, "Robustness and Interpretability." We spoke with
 Madry, a leader in this emerging field, about some of the key ideas
 raised during the event." ...

-- 
__          __
#_ < |\| |< _#

Back to comp.misc | Previous | Next — Next in thread | Find similar | Unroll thread

Thread

3Q: Aleksander Madry on building trustworthy artificial intelligence not@telling.you.invalid (Computer Nerd Kev) - 2019-01-07 22:09 +0000
  Re: 3Q: Aleksander Madry on building trustworthy artificial intelligence RS Wood <rsw@therandymon.com> - 2019-01-14 00:55 +0000
    Re: 3Q: Aleksander Madry on building trustworthy artificial intelligence RS Wood <rsw@therandymon.com> - 2019-01-14 03:17 +0000
      Re: 3Q: Aleksander Madry on building trustworthy artificial intelligence not@telling.you.invalid (Computer Nerd Kev) - 2019-01-14 22:16 +0000
        Re: 3Q: Aleksander Madry on building trustworthy artificial intelligence Bruce Horrocks <07.013@scorecrow.com> - 2019-01-14 23:03 +0000
          Re: 3Q: Aleksander Madry on building trustworthy artificial intelligence Computer Nerd Kev <not@telling.you.invalid> - 2019-01-15 05:50 +0000

csiph-web