Boosting Adversarial Attacks with Momentum — HN submission

Fri, 15 Jun 2018 11:14:38 GMT

Boosting Adversarial Attacks with Momentum

1 point; 0 discussion replies on HN. Paper and source history. A submission is not an endorsement.

Boosting Adversarial Attacks with Momentum — mentioned by nealeratzlaff

Tue, 02 Jan 2018 22:53:55 GMT

I think for most people that hurdle of understanding is immense, and isn't likely to get any better. ML/DL infrastructure will continue to improve and deploying AI systems will become more accessible as time goes on. But I don't see familiarity with (non) convex optimization, statistical learning, topology, etc. becoming mainstream. Without these its hard to see a reasonable path forward for AI. For me this year in DL was a lot narrower. it mostly revolved around systems becoming more human in capability. I think most of this is in the article already: We can now hopefully say that ImageNet…

Paper and discussion history. A mention is not an endorsement.

Boosting Adversarial Attacks with Momentum · HackerPapers discussions

Boosting Adversarial Attacks with Momentum — HN submission

Boosting Adversarial Attacks with Momentum — mentioned by nealeratzlaff