arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1406.2661stat.MLcs.LG
收藏

生成对抗网络

Generative Adversarial Networks

Université de Montréal(蒙特利尔大学);Indian Institute of Technology Delhi(德里印度理工学院);Ecole Polytechnique(巴黎综合理工学院)

Ian J. Goodfellow, Jean Pouget-Abadie, Mehdi Mirza, Bing Xu, David Warde-Farley, Sherjil Ozair, Aaron Courville, Yoshua Bengio

摘要:

我们提出了一个通过对抗过程来估计生成模型的新框架,在这个框架中,我们同时训练两个模型:一个是捕获数据分布的生成模型G,另一个是估计样本来自训练数据而不是G的概率的判别模型D。G的训练过程是最大化D犯错误的概率。这个框架对应于一个极大极小两人博弈。在任意函数G和D的空间中,存在唯一解,其中G恢复训练数据分布,并且D处处等于1/2。在G和D由多层感知器定义的情况下,整个系统可以用反向传播来训练。在样本的训练或生成期间,不需要任何马尔可夫链或展开的近似推理网络。实验表明,通过生成的样本的定性和定量评价的框架的潜力。

英文摘要:

We propose a new framework for estimating generative models via an adversarial process, in which we 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. There is no need for any Markov chains or unrolled approximate inference networks during either training or generation of samples. Experiments demonstrate the potential of the framework through qualitative and quantitative evaluation of the generated samples.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑