Generative adversarial network based novelty detection using minimized reconstruction error  

作　　者：Huan-gang WANG Xin LI Tao ZHANG 

机构地区：[1]Department of Automation,School of Information Science and Technology,Tsinghua University

出　　处：《Frontiers of Information Technology & Electronic Engineering》2018年第1期116-125,共10页信息与电子工程前沿（英文版）

摘　　要：Generative adversarial network(GAN) is the most exciting machine learning breakthrough in recent years,and it trains the learning model by finding the Nash equilibrium of a two-player zero-sum game.GAN is composed of a generator and a discriminator,both trained with the adversarial learning mechanism.In this paper,we introduce and investigate the use of GAN for novelty detection.In training,GAN learns from ordinary data.Then,using previously unknown data,the generator and the discriminator with the designed decision boundaries can both be used to separate novel patterns from ordinary patterns.The proposed GAN-based novelty detection method demonstrates a competitive performance on the MNIST digit database and the Tennessee Eastman(TE) benchmark process compared with the PCA-based novelty detection methods using Hotelling's T^2 and squared prediction error statistics.Generative adversarial network（GAN） is the most exciting machine learning breakthrough in recent years,and it trains the learning model by finding the Nash equilibrium of a two-player zero-sum game.GAN is composed of a generator and a discriminator,both trained with the adversarial learning mechanism.In this paper,we introduce and investigate the use of GAN for novelty detection.In training,GAN learns from ordinary data.Then,using previously unknown data,the generator and the discriminator with the designed decision boundaries can both be used to separate novel patterns from ordinary patterns.The proposed GAN-based novelty detection method demonstrates a competitive performance on the MNIST digit database and the Tennessee Eastman（TE） benchmark process compared with the PCA-based novelty detection methods using Hotelling＇s T^2 and squared prediction error statistics.

关 键 词：Generative adversarial network（GAN） Novelty detection Tennessee Eastman（TE） process 

分 类 号：TP181[自动化与计算机技术—控制理论与控制工程]