立即打开
Facebook如何教电脑“看”人

Facebook如何教电脑“看”人

Stacey Higginbotham 2015年06月25日
Facebook日前发布了一种名为Moments,使用人脸识别技术的功能。该公司称,只需要不到5秒钟的时间,它的人脸识别技术就能在800万张照片中迅速地找到你的脸,目前准确性可达到98%。不过,凭借更出色的电脑视觉和人工智能技术,这家社交巨擘最终希望实现一个更大的目标——让机器理解人。

    电脑如何学会“看”东西

    这项技术又叫做“卷积神经网络”,名字取自一种名叫“卷积”的数学运算,同时它也从人脑的学习方式中吸取了灵感。人脑的学习主要依靠在神经元之间建立连接,信号在神经元之间传输得越多,这些连接就越密集。同理,当电脑在两幅图像之间建立相似点后,它就向这些相似点分配了一个权数。在卷积神经网络中,我们的目标是训练电脑识别出这些关联之间的权数变化。因此,如果图像相匹配,电脑就能准确地看出来。

    这个过程是极为复杂的,它还涉及各种数学运算,以确定图像的不同方面对于识别过程的影响程度。比如,如果你想训练一台计算机学会识别人脸,背景像素其实并不重要。真正重要和惊人的部分在于,机器会自行学会辨别图像的哪一部分最重要,然后还能对这种关系进行归纳。虽然目前还需要很多人力来教会计算机如何正确地为那些相似点分配权数,但只要这个模型建成了,它就会不断自动归纳。

    这个过程在一台强大的电脑上大概需要几天时间。

    自从在一场争夺最精确人脸识别算法的竞赛上,多伦多大学教授乔弗里?辛顿领衔的研究团队利用卷积神经网络技术赢得冠军以来,该技术基本上已经成为目前所有计算机视觉研究的基础。在那次竞赛上,辛顿团队的测试错误率为15.3%,相比之下,获得第二名的团队的测试错误率则为26.2%。辛顿的团队和他们创办的公司后来被谷歌收购。

    不要上传那张照片!

    随着这类研究不断深入,它可能会对我们的日常生活产生重大影响。当然,在人群中识别人脸的技术有可能会成为政府管制的利器,但另一方面,它也会帮助你更好地管理隐私。比如,随着自动人脸识别技术的大规模应用,上传任何一张照片到Facebook,或整个网络之后,你都可能会收到一条通知。

    比如,如果一名游客在纽约时代广场拍照时,不小心把你也拍到了背景里,那么他在上传这张照片后,你就会收到一条提醒,你也可以选择在那张照片里给你的脸打个码。如果是儿童的话,甚至可能自动打码或删除其形象。乐昆指出,Facebook对这种工具非常感兴趣,不过他也强调,Facebook对机器学习的兴趣要远远超出图像识别本身。

    Facebook的目标是教会电脑学会识别人的情感。显然电脑不可能拥有人类的感受,但人类可以教电脑识别感情以及人们对各种感情的反应。如果电脑达到了这种理解程度,那么如果你喝醉了酒,要上传一张醉态照片的时候,Facebook可能就会提醒你是否真的想这样做。

    “这将不是人脸识别技术”,乐昆表示:“我们不在乎照片里的人是谁。我们会使用其它类型的图像识别技术,然后以不同的方法训练机器,比如说某张照片看起来非常尴尬,我们就会提醒你,确保你是真的想把这张照片公开到网上。”

    目前Facebook尚不具备这样的技术,乐昆也只是假设性地提出了这些概念,以介绍Facebook的人工智能技术会朝着什么方向发展。当然,这种高端的算法技术可能也会令人深感不适。目前Facebook在加拿大和欧盟各国没有启用自动标签功能,就是出于隐私方面的考虑。另外,一想到你在打算上传照片时,电脑还要替你再审查一遍,或是一想到你在发段子的时候,电脑正在努力理解你的笑点,这种感觉的确是令人浑身不舒服。

    乐昆表示:“我们希望让机器变得更加智能,能够理解文字、图像、视频和帖子。总之,任何有可能发生在网络世界的事情,我们都想了解其语境。”由于网上有太多的数码内容,人们的信息很容易被各种各样的其它信息所淹没。而乐昆的团队则可以根据与人们的兴趣和最关注的事情将他们联系在一起。如此复杂的解决方案,只是为了实现一个简单的目标:确保你在Facebook上能看到你想看的东西。

    乐昆表示:“这才是我们在Facebook想要实现的大目标,也就是让机器理解人。”(财富中文网)

    译者:朴成奎

    审校:任文科

    How computers learn to see

    That technique is called convolutional neural networking, and takes its name from both a mathematical operation called a convolution, and inspiration from how the human brain learns. The brain learns by establishing connections between neurons, and the more often a signal is sent over those neurons, the denser those connections get. In a similar vein, when computers establish similarities between two images it assigns a weight to those similarities. In convolutional neural networks, the goal is to train the machine to recognize the changes in weights between those connections so it can tell with increasing accuracy if the image matches.

    The process of doing this is incredibly complicated and involves different calculations that work to establish how important certain aspects of the image are to the actual process of recognizing what the image is. For example, if you want to train a computer to recognize faces, the pixels related to the background are less important. The tricky—and frankly amazing— part of this is that the machine learns on its own how to tell what part of the image is most relevant, and then can generalize those relationships going forward. It still takes a lot of human effort to nudge the computer into recognizing the right way to weight the similarities, but once the model is built, it can generalize going forward.

    The process can take a few days on a powerful computer.

    Convolutional neural networks have become the basis for almost all of the computer vision research done today, after a team of researchers led by Geoffrey Hinton at the University of Toronto, used that technique to win a competition where image recognition algorithms vie to be most accurate. Hinton, whose team and startup were lateracquired by Google, won the competition with a test error rate of 15.3%, compared to 26.2% for the second-place winner.

    Don’t post that photo!

    As research continues, the opportunities for use in our day-to-day life are significant. Yes, there is the ability to match people’s faces in a crowd that might lead to greater government surveillance, but there is also an opportunity to use better facial recognition to manage your privacy. For example, with automatic facial recognition at scale, any picture of you uploaded to Facebook (or perhaps even the web) could result in a notification.

    For example, if you are somehow captured in the background of a tourist shot of Times Square, you could get a notification and the option to blur your face. Applied to children, the blurring or removal could be automated. LeCun notes that Facebook is interested in such tools, but also stresses that Facebook’s interest in machine learning goes far beyond image recognition.

    Facebook’s goal is to get a computer to understand empathy. Obviously, it won’t be able to feel what humans do, but it can be trained to recognize what emotions are and how people will react. With that level of understanding, Facebook could, say, offer a warning when you are about to post a photo of you drunk and ask if you really want to do that.

    “This would not be face recognition,” said LeCun. “We don’t care who is in the picture. We would use other types of image recognition and train them differently to say that this looks embarrassing and then tap you on the shoulder to make sure you want to post this publicly.”

    This isn’t something Facebook can do today, but LeCun offered these concepts as a thought experiment to show where Facebook could head with its AI research. Of course, this sort of expertise informed by an algorithm can make people deeply uncomfortable. Today Facebook doesn’t turn on its auto tagging features in countries like Canada and the EU because of privacy concerns, and there’s a certain creep factor in having a computer second guess your photo-sharing choices or having software trying to parse your jokes to try to understand what you find funny.

    “What we’d like to do is make machines more intelligent, understanding text, images, videos and posts,” LeCun said. “Anything that can happen in the digital world we want to understand the context.” Because there is so much digital content people could easily become overwhelmed by the information flooding their feeds. The efforts of LeCun’s team will help connect people with the content that is most relevant to their interests and priorities. It’s a complex solution to a simple goal: to make sure that you see what you want to see on Facebook.

    “That’s the big mission that we at Facebook are trying to fulfill,” LeCun said. “Machines that understand people.”

  • 热读文章
  • 热门视频
活动
扫码打开财富Plus App