Does Deep Learning Have Deep Flaws?

Re:Does Deep Learning Have Deep Flaws? by kilbasa on Thursday June 19, 2014 @01:22PM (#7917204)

IIRC even the human brain has the 'adversarial' image flaw (these images will be unique to each person), but one simple workaround is to alter the input image via eye movement (which happens unconsciously).

[ Parent | on HN ]

Re:Does Deep Learning Have Deep Flaws? by codeflo on Thursday June 19, 2014 @02:02PM (#7917401)

IIRC? Can you provide any source or example? This sounds very interesting.

[ Parent | on HN ]

Re:Does Deep Learning Have Deep Flaws? by kilbasa on Thursday June 19, 2014 @02:31PM (#7917562)

There was a discussion on slashdot (take it with a grain of salt perhaps) about a similar article.

http://slashdot.org/story/14/05/27/1326219/the-flaw-lurking-...

The comment I recalled was written by someone with the handle "presidenteloco".

[ Parent | on HN ]