On 2017-02-22 15:51, Dr Miles Dyson wrote:
If the world is such that the data that exists supports empirical and scientific racism (or insert your politically incorrect world view here), how could we create a AGI that could avoid (or minimize the likelihood of it) taking such an undesirable view?
This topic has been in the tech news quite a bit recently. Late last year there was a "big" paper published on the topic from Moritz Hardt, Eric Price and Nathan Srebro. Follow the links in the following blog post for the free PDF: "Equality of Opportunity in Supervised Learning" https://research.googleblog.com/2016/10/equality-of-opportunity-in-machine.html -- __________ |im |yler http://timtyler.org/ ------------------------------------------- AGI Archives: https://www.listbox.com/member/archive/303/=now RSS Feed: https://www.listbox.com/member/archive/rss/303/21088071-f452e424 Modify Your Subscription: https://www.listbox.com/member/?member_id=21088071&id_secret=21088071-58d57657 Powered by Listbox: http://www.listbox.com
