Towards Principled Methods for Training Generative Adversarial Networks — 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.

Towards Principled Methods for Training Generative Adversarial Networks · HackerPapers discussions

Towards Principled Methods for Training Generative Adversarial Networks — mentioned by nealeratzlaff