Evolving Deep Neural Networks · HackerPapers discussions

Evolving Deep Neural Networks — mentioned by ofrancon

Thu, 22 Mar 2018 19:09:06 GMT

A few links you can look at if you're interested in neuroevolution, from the same group of researchers: Ken Stanley and Risto Miikkulainen original NEAT (NeuroEvolution of Augmenting Topologies) paper: http://nn.cs.utexas.edu/downloads/papers/stanley.ec02.pdf Ken Stanley's novelty search page, and a link to his book, "Why Greatness Cannot Be Planned: The Myth of the Objective": http://eplex.cs.ucf.edu/noveltysearch/userspage/ Risto Miikkulainen's Evolving Deep Neural Networks paper: https://arxiv.org/abs/1703.00548 Ken Stanley & team's work at Uber, with links to some recent papers…

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

Evolving Deep Neural Networks — mentioned by indescions_2017

Thu, 13 Jul 2017 23:04:01 GMT

The Asteroids demo is cool too: https://xviniette.github.io/AsteroidsLearning/ AI Lab at UTexas Austin has more Atari 2600 NEAT demos as well. The Kung Fu Master "button masher" style makes me think a Street Fighter V agent would be hilarious to see in Human vs AI competitive action! http://www.cs.utexas.edu/~ai-lab/?atari For a proof of concept, this shows the capability of ML in a web browser. Creating an ad hoc cluster of a hundred webrtc peers would yield a formidable (but slow) meta learner. And just to put it in perspective: sentient.ai's petascale darkcycle cluster consists of ~1M CPUs…

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

Evolving Deep Neural Networks — HN submission

Tue, 14 Mar 2017 16:32:44 GMT

Evolving Deep Neural Networks

26 points; 6 discussion replies on HN. Paper and source history. A submission is not an endorsement.