InfoGAN: Interpretable Representation Learning by Information Maximizing Generative Adversarial Nets · HackerPapers discussions

InfoGAN: Interpretable Representation Learning by Information Maximizing Generative Adversarial Nets — mentioned by kdoherty

Tue, 19 Sep 2017 16:03:42 GMT

I'm assuming by iterate you mean "generate outputs of a GAN which preserve some order that you can iterate through." The answer is yes, but not in the way that one might think. Despite the fact that we seed the GAN with input noise, there is no guarantee that the GAN makes use of this at all. This is a theme with GANs: we often want to imbue them with prior knowledge that we think is important, but is easily ignored by the GAN. In this case, we want to generate samples from p(x|z), where x is in the space of our data (often images, in this case passwords), but provided it gets good results…

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

InfoGAN: Interpretable Representation Learning by Information Maximizing Generative Adversarial Nets — mentioned by fiter

Thu, 06 Apr 2017 21:04:54 GMT

The paper I was thinking of is called: "InfoGAN: Interpretable Representation Learning by Information Maximizing Generative Adversarial Nets"[0]. I do not have experience training and investigating neural nets, but from what I read in that paper, there's no reason to presume you'll find neurons that represent a feature you're interested in. In the paper they alter the reward function to get neurons that correspond to the features they are interested in. [0] https://arxiv.org/pdf/1606.03657v1.pdf

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

InfoGAN: Interpretable Representation Learning by Information Maximizing Generative Adversarial Nets — mentioned by pinouchon

Mon, 06 Feb 2017 09:05:45 GMT

I read the infoGAN paper yesterday. It blew my mind. https://arxiv.org/pdf/1606.03657v1.pdf. This is a way to do disentangled feature representation learning without supervision.

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

InfoGAN: Interpretable Representation Learning by Information Maximizing Generative Adversarial Nets — mentioned by nl

Wed, 11 Jan 2017 03:07:04 GMT

GANs (and InfoGAN[0] in particular) has shown there are still pretty huge breakthoughs out there. Some other things you may be interested in: Learning to learn by gradient descent by gradient descent[1] Neural Architecture Search with Reinforcement Learning[2] [0] https://arxiv.org/abs/1606.03657, https://arxiv.org/pdf/1701.00160.pdf [1] https://arxiv.org/abs/1606.04474 [2] https://openreview.net/pdf?id=r1Ue8Hcxg

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

InfoGAN: Interpretable Representation Learning by Information Maximizing Generative Adversarial Nets — mentioned by nl

Wed, 17 Aug 2016 04:17:04 GMT

They have plenty of results. All their work on GANs[1][2] has been great, and the OpenAI gym has proven to be pretty popular for reinforcement learning research already. I'm not sure how "hype" is measured - perhaps people thought they were going to invent some kind of AI entity we would have to persuade not to shoot us all by now or something. I know that all the papers coming out of OpenAI get hyped just as much as anything from DeepMind, Google Brain or FAIR, so there seems to be decent amount of hype still? But then usually that hype is justified, in which case maybe it is better…

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

InfoGAN: Interpretable Representation Learning by Information Maximizing Generative Adversarial Nets — HN submission

Fri, 08 Jul 2016 15:44:21 GMT

InfoGAN: Representation Learning by Generative Adversarial Nets

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

InfoGAN: Interpretable Representation Learning by Information Maximizing Generative Adversarial Nets — mentioned by andreyk

Thu, 16 Jun 2016 20:51:48 GMT

Brief summary: a nice intro about what generative models are and the current popular approaches/papers, followed by descriptions of recent work by OpenAI in the space. Quick links to papers mentioned: Improving GANs https://arxiv.org/abs/1606.03498 Improving VAEs http://arxiv.org/abs/1606.04934 InfoGAN https://arxiv.org/abs/1606.03657 Curiosity-driven Exploration in Deep Reinforcement Learning via Bayesian Neural Networks http://arxiv.org/abs/1605.09674 Generative Adversarial Imitation Learning http://arxiv.org/abs/1606.03476 I think the last one seems very exciting, I expect Imitation…

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