论文总结：Gan papers summary

Generative Adversarial Nets (GAN)

论文地址

Conditional Generative Adversarial Nets (CGAN)

论文地址

Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks (DCGAN)

论文地址

Deep Generative Image Models using a Laplacian Pyramid of Adversarial Networks（LAPGAN）

论文地址

Generative Adversarial Nets (GAN)

• 论文想要解决什么问题（动机motivation）
  Due to the difficulty of approximating many intractable probabilistic computations that arise in maximum likelihood estimation and related strategies, and due to difficulty of leveraging the benefits of piecewise linear units in the generative context, Deep generative models have had less of an impact than backpropagation and dropout algorithms for discriminative models, one of the most striking successes.
  由于难以逼近最大似然估计和相关策略中出现的许多棘手的概率计算，以及很难利用生成上下文中分段线性单元的优势，比之于backpropagation和dropout算法，深度生成模型对discrimiinative模型——深度学习领域最成功的模型之一产生的影响很小。
• 解决思路和方案是什么
  They propose a new framework for estimating generative models via an adversarial process, in which they simultaneously train two models: a generative model G that captures the data distribution, and a discriminative model D that estimates the probability that a sample came from the training data rather than G. The training procedure for G is to maximize the probability of D making a mistake. This framework corresponds to a minimax two-player game. In the space of arbitrary functions G and D, a unique solution exists, with G recovering the training data distribution and D equal to 1/2 everywhere. In the case where G and D are defined by multilayer perceptrons, the entire system can be trained with backpropagation