计算机科学
人工智能
生成对抗网络
生成语法
对抗制
机器学习
模式识别(心理学)
鉴别器
分类器(UML)
人工神经网络
深度学习
发电机(电路理论)
电信
探测器
量子力学
物理
功率(物理)
作者
Shabab Bazrafkan,Hossein Javidnia,Peter Corcoran
出处
期刊:Cornell University - arXiv
日期:2018-05-01
被引量:3
摘要
One of the most interesting challenges in Artificial Intelligence is to train conditional generators which are able to provide labeled adversarial samples drawn from a specific distribution. In this work, a new framework is presented to train a deep conditional generator by placing a classifier in parallel with the discriminator and back propagate the classification error through the generator network. The method is versatile and is applicable to any variations of Generative Adversarial Network (GAN) implementation, and also gives superior results compared to similar methods.
科研通智能强力驱动
Strongly Powered by AbleSci AI