艺术与机器人

Generative adversarial networks and their creative potential.

生成式对抗网络及其创造潜力。

by Peter Suechting

彼得·苏希汀(Peter Suechting)

Initial appraisals of the portrait Edmond de Belamy placed its worth somewhere between $7,000 and $10,000. Indeed, the painting itself is nothing special. In muddy swatches of brown, black, white, and gray, it depicts a rather blurry man staring bleakly and confusedly out of the frame. But on October 25th, 2018, when the dust settled in Christie’s New York auction house, the portrait had sold for $432,500.

对肖像埃德蒙·德·贝拉米(Edmond de Belamy)的初步评估将其价值定在7,000美元至10,000美元之间。 确实，这幅画本身并没有什么特别的。 在棕色，黑色，白色和灰色的泥泞样本中，它描绘了一个模糊的人，茫然而困惑地凝视着画框。 但是在2018年10月25日，当灰尘落在佳士得纽约拍卖行时 ， 这幅肖像以432,500美元售出 。

人Craft.io术 (The art in artificial)

What drove such a frenzy of bidding on behalf of the participants present that afternoon on the Christie’s auction floor? The fact that it had been “painted” by a machine. The Belamy portrait series is the work of Obvious, a collective of three French artists and programmers, that produced it by training a generative adversarial network, or GAN, on a dataset of 15,000 European portraits.¹ The output? Eleven unique portraits, including Edmond de Belamy, with features informed by those of the training set.

是什么驱使代表当天下午在佳士得拍卖场上参加的投标人如此疯狂？ 它已经被机器“涂漆”的事实。 Belamy肖像系列是由三位法国艺术家和程序员组成的Obvious的作品，是通过在15,000张欧洲肖像的数据集上训练生成性对抗网络(GAN)而制作的。¹ 包括埃德蒙·德·贝拉米 ( Edmond de Belamy)在内的11幅独特肖像，其特征来自训练背景。

Christie’s. 佳士得(Christie's)提供 。

The project portrays AI artwork as potentially of equal merit to human-produced art. After all, Obvious essentially copied their favorite algorithmic output result using an inkjet printer, framed it in gold, and signed it with a fragment of algorithmic code. There’s nothing special about the object itself; it could be printed out and framed a thousand more times. By this logic, the bidding war over the Belamy portrait appears to be about owning a piece of history in the making: the moment machines became artists themselves.

该项目将AI艺术作品描述为与人类艺术具有同等价值。 毕竟， Obvious本质上使用喷墨打印机复制了他们最喜欢的算法输出结果，将其用金色框起来，并用一段算法代码对其进行了签名。 对象本身没有什么特别的。 它可以被打印出来并装裱一千多次。 按照这种逻辑，对Belamy肖像的竞购战似乎是在拥有制作中的一段历史：机器成为艺术家本身的那一刻。

Machines create, but can machines be creative? This is the question prompted by the emergence of GANs. For programmers like Obvious, GANs seem to represent a powerful means to purposefully intervene in the discourse about authenticity. As such, the Belamy project is ultimately part of a broader swell of debate around the definition of creativity, and whether humans can lay claim to being its exclusive practitioners.

机器可以创造，但是机器可以创造吗？ 这是GAN的出现提示的问题。 对于像Obvious这样的程序员， GAN似乎代表了一种有目的地干预真实性的有力手段。 因此， Belamy项目最终成为围绕创造力定义以及人类是否可以声称自己是其独有实践者的广泛辩论的一部分。

错误产生 (To err is generative)

Since their inception in the mind of Ian Goodfellow, GANs have been deployed in a broad variety of “creative” tasks. According to Goodfellow et al.’s 2014 paper, generative adversarial networks (GANs) train two models — a generator, and a discriminator — at the same time. An original dataset (images, text, etc.) is fed into both algorithms, each of which pulls the data apart and assesses how its components are related to one another. This is a typical application of neural networks. But what comes next is key to the process. The mythology of the moment has Goodfellow posing a simple question: “what if neural networks could compete with one another?”

自从伊恩·古德费洛(Ian Goodfellow)想到它们以来，GAN已被部署在各种各样的“创造性”任务中。 根据Goodfellow等人2014年的论文 ，生成对抗网络(GAN)可以同时训练两个模型-生成器和鉴别器。 将原始数据集(图像，文本等)输入两种算法，每种算法都将数据拆开并评估其组成部分 彼此相关。 这是神经网络的典型应用。 但是接下来是该过程的关键。 当下的神话让古德费洛提出了一个简单的问题：“神经网络能否相互竞争？”

Within GANs, the adversarial network framework is also linked to an operation called “back-propagation,” which is a critical component of the learning process. The Skymind.AI Wiki analogizes,

在GAN中，对抗网络框架还链接到称为“ 反向传播 ”的操作，这是学习过程的关键组成部分。 该Skymind.AI维基类推 ，

“… a neural network to a large piece of artillery that is attempting to strike a distant object with a shell. When the neural network makes a guess about an instance of data, it fires, a cloud of dust rises on the horizon, and the gunner tries to make out where the shell struck, and how far it was from the target. That distance from the target is the measure of error. The measure of error is then applied to the angle and direction of the gun (parameters), before it takes another shot. Back-propagation takes the error associated with a wrong guess by a neural network, and uses that error to adjust the neural network’s parameters in the direction of less error.”

“……一个大型火炮的神经网络，正试图用炮弹击中一个遥远的物体。 当神经网络对数据实例进行猜测时，它会着火，地平线上升起一团尘埃，而炮手则试图找出炮弹击中的位置以及它与目标的距离。 距目标的距离是误差的量度。 然后在再次射击之前，将误差的度量应用于枪的角度和方向(参数)。 反向传播采用了与神经网络错误猜测有关的错误，并使用该错误将神经网络的参数朝着更少错误的方向调整。”

Back-propagation is similar to human cognition in this way. An artillery operator, firing off a few shells to test and refine his range and aim before zeroing in on the input parameters that drop shells in the target area, learns about what’s working, what needs adjustment, and automatically makes those adjustments on each “shot.” But whereas the human artillery operation must rely on his own eyes to ascertain the degree to which he has succeeded or failed, GANs have the discriminator algorithm, which tells it whether or not the simulacra it’s been passed are discernibly fake. Additionally, a machine can fire off thousands of “shots” in the time it takes a human to fire once. The iterative power of machine calculation thus allows both networks to quickly co-evolve.

反向传播在这种方式上类似于人类的认知。 炮兵操作员发射一些炮弹，以测试和完善射程，然后瞄准将炮弹投到目标区域的输入参数，然后了解工作原理，需要调整的内容，并在每次“射击”时自动进行调整。” 但是，尽管人类炮兵行动必须依靠他自己的眼睛来确定他成功或失败的程度，但GAN拥有鉴别器算法，该算法可以告诉它通过的模拟武器是否明显是假的。 此外，一台机器可以在人类开火一次的时间内发射出数千个“子弹”。 因此，机器计算的迭代能力使两个网络都能快速协同发展。

In sum, back-propagation creates an environment in which a generation algorithm is quickly and effectively trained to a very high degree by competing against a similarly trainable discriminator algorithm. The generator algorithm is effectively unbounded in the degree of skill it can attain relative to the discriminator. Through this process, fakery asymptotically approaches reality to the point that discerning between the two is no longer possible, even for machines. So, after proper training has progressed, the generator algorithm becomes capable of producing simulacra that can fool the digital eye of the discriminator, and consequently, the human eye observing the result.

总之，反向传播创造了一种环境，在该环境中，通过与类似的可训练鉴别器算法竞争，可以非常快速，有效地对生成算法进行训练。 生成器算法相对于鉴别器实际上可以达到的技术水平是不受限制的。 通过这个过程，伪造渐近地逼近现实，以至于即使对于机器，两者之间的区别也不再可能。 因此，在进行了适当的训练之后，生成器算法将能够生成可以使鉴别器的数字眼睛蒙蔽的仿真器，从而使人眼可以观察到结果。

混合现实 (Remixing reality)

There are numerous examples of GAN-based tools in recent years, ranging from well-known and predatory applications like “deepfakes” to more enlightened applications like DeepDream which developed GAN-based tools for generating haunting, hallucinogenic imagescapes from real photo inputs. Project Magenta, a collective of Google-affiliated researchers, develops and hosts a library of GAN-based tools for augmenting digital music production, providing another fascinating application of the technique to audio manipulation and enhancement. (You can hear the results of Magenta’s collaboration with LA-based band YACHT on the latter’s September 2019 album here. And below is an example of video interpolation using GAN-based tools to project bodies onto movement, presented in a recent paper by Caroline Chan.)

近年来，基于GAN的工具有很多例子，从众所周知的掠食性应用程序(如“ Deepfakes ”)到更开明的应用程序(如DeepDream) ， DeepDream开发了基于GAN的工具，可从真实的照片输入中生成令人困扰的幻觉图像。 由Google旗下的研究人员组成的Magenta项目开发并托管了一个基于GAN的工具库，用于增强数字音乐的制作，为该技术在音频处理和增强方面的另一个引人入胜的应用。 (你可以听到Magenta公司合作的基于LA-带游艇上的结果，后者的2019年9月的专辑在这里 ，并在下面的视频插的例子 使用基于GAN的工具将身体投射到运动上， 这是Caroline Chan的最新论文提出的 。)

“Do as I do” motion transfer by Chan et al. 2019.

Chan等人的“做我做”运动转移。 2019。

But lest we think that AI researchers spend their time attempting to put already-starving artists out of business, these artistic applications are not ready to compete with the grand masters, yet. They remain tools to be employed to varying degrees of usefulness by humans. Artistic applications aside, however, GAN-based tools are making inroads into other realms, a topic explored in other posts.

但是，为了避免AI研究人员花时间尝试将已经挨饿的艺术家从生意中淘汰出去，这些艺术应用程序尚未准备好与大师们竞争。 它们仍然是人类要在不同程度上使用的工具。 除了艺术性的应用程序之外，基于GAN的工具正在侵入其他领域，这是其他文章中探讨的主题。

For the past two years, researchers at MIT’s Data-to-AI Lab have been experimenting with using GANS to solve a number of interesting and societally-relevant problems, ranging from passing (and detecting) secret messages and protecting videos via watermarking to identifying anomalies and preserving privacy. The DAI Lab is excited to share some of our more exciting projects with the machine learning and data science communities with the hopes of sparking discussion and collaboration. To that end, this article is the first in a multipart series on the lab’s GAN-related projects, to include demonstrations of our work, tutorials, commentary essays, and open-source libraries. We plan to release these articles bi-weekly, alternating with a series of tutorial posts devoted to several of our recent GAN-related projects. Check back for more soon on our Medium page, and please follow us on Twitter.

在过去的两年中，麻省理工学院数据到AI实验室的研究人员一直在尝试使用GANS解决许多有趣且与社会相关的问题，从传递(和检测)秘密消息到通过加水印保护视频到识别异常，不等并保护隐私。 DAI实验室很高兴与机器学习和数据科学界共享我们一些更令人兴奋的项目，希望引发讨论和合作。 为此，本文是该实验室GAN相关项目的多部分系列中的第一篇，其中包括我们的工作演示，教程，评论文章和开源库。 我们计划每两周发布这些文章，并提供一系列专门针对我们最近与GAN相关的项目的教程帖子。 请在我们的“中型”页面上查看更多内容，然后在 Twitter上 关注我们 。

[1]: Debate persists as to the origin of the code that Obvious used to produce the Belamy portrait. Programmer Robbie Barat , an AI artist unaffiliated with Obvious, is responsible for, by some accounts, 90% of the code used in the project, although he had originally posted the code as part of the creative commons.

[1]：关于Obvious用于产生Belamy肖像的代码的起源，辩论仍然存在。 程序员罗比·巴拉 ，一个AI艺术家附属于明显 ，负责， 一些帐户 ，90％在项目中使用，虽然他最初发布的代码作为创作共用的部分代码。

翻译自: https://medium.com/mit-data-to-ai-lab/art-robots-661b7ad86411