CAN: Creative Adversarial Networks, Generating "Art" by Learning About Styles and Deviating from Style Norms · HackerPapers discussions

CAN: Creative Adversarial Networks, Generating "Art" by Learning About Styles and Deviating from Style Norms — HN submission

Mon, 17 Sep 2018 18:52:27 GMT

CAN: Generating Art by Learning About Styles and Deviating from Style Norms

37 points; 9 discussion replies on HN. Paper and source history. A submission is not an endorsement.

CAN: Creative Adversarial Networks, Generating "Art" by Learning About Styles and Deviating from Style Norms — mentioned by radarsat1

Thu, 06 Jul 2017 16:14:06 GMT

I think it's a very interesting question, of how can we measure when a neural network is being creative? In fact, creativity is not obvious at all. It's sort of an ill-posed question if you think about it. How can you verify that a network is generating things that are not like what it was trained on, yet are... like what it was trained on? Are neural networks* forever relegated to the role of copying and interpolation? Do the neural network weights form a kind of database? * (I don't think this only applies to neural networks, but models in general) There was one recent work trying to…

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

CAN: Creative Adversarial Networks, Generating "Art" by Learning About Styles and Deviating from Style Norms — HN submission

Tue, 04 Jul 2017 01:57:18 GMT

Creative Adversarial Networks Generating “Art”

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

CAN: Creative Adversarial Networks, Generating "Art" by Learning About Styles and Deviating from Style Norms — HN submission

Fri, 30 Jun 2017 19:57:51 GMT

Generating “Art” by Learning About Styles and Deviating from Style Norms

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