自动化学报2018，Vol.44Issue(5)：793-803,11.DOI:10.16383/j.aas.2018.c170600
一种能量函数意义下的生成式对抗网络
A Generative Adversarial Network Based on Energy Function
摘要
Abstract
Generative adversarial network (GAN) has become a hot research in artificial intelligence, and has received much attention from scholars. In view of low efficiency of generative model and gradient disappearance of discriminative model, a GAN based on energy function (E-REGAN) is proposed in this paper, in which reconstruction error (RE) acts as the energy function. Firstly, an adaptive deep belief network (ADBN) is presented as the generative model, which is used to fast learn the probability distribution of given sample data and further generate new data with similar probability distribution. Secondly,the RE in adaptive deep auto-encoder(ADAE)acts as an energy function evaluating the performance of discriminative model;the smaller energy function,the closer to Nash equilibrium the learning optimization process of GAN will be, and vice versa. Meanwhile, the stability analysis of the proposed E-REGAN is given using the inverse inference method. Finally,the simulation results from MNIST and CIFAR-10 benchmark dataset experiments show that, compared with the existing similar models, the proposed E-REGAN achieves significant improvement in learning rate and data generation capability.关键词
生成式对抗网络/能量函数/重构误差/自适应深度信念网络/自适应深度自编码器/纳什均衡Key words
Generative adversarial network (GAN)/energy function/reconstruction error (RE)/adaptive deep belief network(ADBN)/adaptive deep auto-encoder(ADAE)/Nash equilibrium引用本文复制引用
王功明,乔俊飞,王磊..一种能量函数意义下的生成式对抗网络[J].自动化学报,2018,44(5):793-803,11.基金项目
国家自然科学基金(61533002)资助 Supported by National Natural Science Foundation of China(61533002) （61533002）
