Recently I've read an interesting paper about unsupervised learning: The Information Sieve Greg Ver Steeg and Aram Galstyan, ICML 2016, http://arxiv.org/abs/1507.02284 I really like the paper. In thei...
Recently I've read an interesting paper about unsupervised learning: The Information Sieve Greg Ver Steeg and Aram Galstyan, ICML 2016, http://arxiv.org/abs/1507.02284 I really like the paper. In thei...
If you ask deep learning people "what is the best image generation model now", many of them would probably say "generative adversarial networks" (GAN). The original paper describes an adversarial proc...
Here's a general case that the 1-step learning will failed to achieve the optimal parameters, inspired by [1]. Consider the exponential family model where (we can also consider it as a multi-expert ...