While the costs of human violence have attracted a great deal of attention
from the research community, the effects of the network-on-network (NoN)
violence popularised by Generative Adversarial Networks have yet to be
addressed. In this work, we quantify the financial, social, spiritual,
cultural, grammatical and dermatological impact of this aggression and address
the issue by proposing a more peaceful approach which we term Generative
Unadversarial Networks (GUNs). Under this framework, we simultaneously train
two models: a generator G that does its best to capture whichever data
distribution it feels it can manage, and a motivator M that helps G to achieve
its dream. Fighting is strictly verboten and both models evolve by learning to
respect their differences. The framework is both theoretically and electrically
grounded in game theory, and can be viewed as a winner-shares-all two-player
game in which both players work as a team to achieve the best score.
Experiments show that by working in harmony, the proposed model is able to
claim both the moral and log-likelihood high ground. Our work builds on a rich
history of carefully argued position-papers, published as anonymous YouTube
comments, which prove that the optimal solution to NoN violence is more GUNs.
Описание
[1703.02528] Stopping GAN Violence: Generative Unadversarial Networks
%0 Generic
%1 albanie2017stopping
%A Albanie, Samuel
%A Ehrhardt, Sébastien
%A Henriques, João F.
%D 2017
%K 2017 GAN arxiv deep-learning paper
%T Stopping GAN Violence: Generative Unadversarial Networks
%U http://arxiv.org/abs/1703.02528
%X While the costs of human violence have attracted a great deal of attention
from the research community, the effects of the network-on-network (NoN)
violence popularised by Generative Adversarial Networks have yet to be
addressed. In this work, we quantify the financial, social, spiritual,
cultural, grammatical and dermatological impact of this aggression and address
the issue by proposing a more peaceful approach which we term Generative
Unadversarial Networks (GUNs). Under this framework, we simultaneously train
two models: a generator G that does its best to capture whichever data
distribution it feels it can manage, and a motivator M that helps G to achieve
its dream. Fighting is strictly verboten and both models evolve by learning to
respect their differences. The framework is both theoretically and electrically
grounded in game theory, and can be viewed as a winner-shares-all two-player
game in which both players work as a team to achieve the best score.
Experiments show that by working in harmony, the proposed model is able to
claim both the moral and log-likelihood high ground. Our work builds on a rich
history of carefully argued position-papers, published as anonymous YouTube
comments, which prove that the optimal solution to NoN violence is more GUNs.
@misc{albanie2017stopping,
abstract = {While the costs of human violence have attracted a great deal of attention
from the research community, the effects of the network-on-network (NoN)
violence popularised by Generative Adversarial Networks have yet to be
addressed. In this work, we quantify the financial, social, spiritual,
cultural, grammatical and dermatological impact of this aggression and address
the issue by proposing a more peaceful approach which we term Generative
Unadversarial Networks (GUNs). Under this framework, we simultaneously train
two models: a generator G that does its best to capture whichever data
distribution it feels it can manage, and a motivator M that helps G to achieve
its dream. Fighting is strictly verboten and both models evolve by learning to
respect their differences. The framework is both theoretically and electrically
grounded in game theory, and can be viewed as a winner-shares-all two-player
game in which both players work as a team to achieve the best score.
Experiments show that by working in harmony, the proposed model is able to
claim both the moral and log-likelihood high ground. Our work builds on a rich
history of carefully argued position-papers, published as anonymous YouTube
comments, which prove that the optimal solution to NoN violence is more GUNs.},
added-at = {2018-02-01T19:37:47.000+0100},
author = {Albanie, Samuel and Ehrhardt, Sébastien and Henriques, João F.},
biburl = {https://www.bibsonomy.org/bibtex/24736f8527fad96fd28270b4cc2afe848/achakraborty},
description = {[1703.02528] Stopping GAN Violence: Generative Unadversarial Networks},
interhash = {b0753104e03498b15a497ae900f4f944},
intrahash = {4736f8527fad96fd28270b4cc2afe848},
keywords = {2017 GAN arxiv deep-learning paper},
note = {cite arxiv:1703.02528Comment: Under review as a conference paper at SIGBOVIK 2017},
timestamp = {2018-02-01T19:37:47.000+0100},
title = {Stopping GAN Violence: Generative Unadversarial Networks},
url = {http://arxiv.org/abs/1703.02528},
year = 2017
}