成人小说亚洲一区二区三区,亚洲国产精品一区二区三区,国产精品成人精品久久久,久久综合一区二区三区,精品无码av一区二区,国产一级a毛一级a看免费视频,欧洲uv免费在线区一二区,亚洲国产欧美中日韩成人综合视频,国产熟女一区二区三区五月婷小说,亚洲一区波多野结衣在线

立即打開
Facebook如何教電腦“看”人

Facebook如何教電腦“看”人

Stacey Higginbotham 2015年06月25日
Facebook日前發(fā)布了一種名為Moments,使用人臉識別技術(shù)的功能。該公司稱,只需要不到5秒鐘的時間,它的人臉識別技術(shù)就能在800萬張照片中迅速地找到你的臉,目前準確性可達到98%。不過,憑借更出色的電腦視覺和人工智能技術(shù),這家社交巨擘最終希望實現(xiàn)一個更大的目標——讓機器理解人。

????電腦如何學會“看”東西

????這項技術(shù)又叫做“卷積神經(jīng)網(wǎng)絡”,名字取自一種名叫“卷積”的數(shù)學運算,同時它也從人腦的學習方式中吸取了靈感。人腦的學習主要依靠在神經(jīng)元之間建立連接,信號在神經(jīng)元之間傳輸?shù)迷蕉?,這些連接就越密集。同理,當電腦在兩幅圖像之間建立相似點后,它就向這些相似點分配了一個權(quán)數(shù)。在卷積神經(jīng)網(wǎng)絡中,我們的目標是訓練電腦識別出這些關(guān)聯(lián)之間的權(quán)數(shù)變化。因此,如果圖像相匹配,電腦就能準確地看出來。

????這個過程是極為復雜的,它還涉及各種數(shù)學運算,以確定圖像的不同方面對于識別過程的影響程度。比如,如果你想訓練一臺計算機學會識別人臉,背景像素其實并不重要。真正重要和驚人的部分在于,機器會自行學會辨別圖像的哪一部分最重要,然后還能對這種關(guān)系進行歸納。雖然目前還需要很多人力來教會計算機如何正確地為那些相似點分配權(quán)數(shù),但只要這個模型建成了,它就會不斷自動歸納。

????這個過程在一臺強大的電腦上大概需要幾天時間。

????自從在一場爭奪最精確人臉識別算法的競賽上,多倫多大學教授喬弗里?辛頓領(lǐng)銜的研究團隊利用卷積神經(jīng)網(wǎng)絡技術(shù)贏得冠軍以來,該技術(shù)基本上已經(jīng)成為目前所有計算機視覺研究的基礎。在那次競賽上,辛頓團隊的測試錯誤率為15.3%,相比之下,獲得第二名的團隊的測試錯誤率則為26.2%。辛頓的團隊和他們創(chuàng)辦的公司后來被谷歌收購。

????不要上傳那張照片!

????隨著這類研究不斷深入,它可能會對我們的日常生活產(chǎn)生重大影響。當然,在人群中識別人臉的技術(shù)有可能會成為政府管制的利器,但另一方面,它也會幫助你更好地管理隱私。比如,隨著自動人臉識別技術(shù)的大規(guī)模應用,上傳任何一張照片到Facebook,或整個網(wǎng)絡之后,你都可能會收到一條通知。

????比如,如果一名游客在紐約時代廣場拍照時,不小心把你也拍到了背景里,那么他在上傳這張照片后,你就會收到一條提醒,你也可以選擇在那張照片里給你的臉打個碼。如果是兒童的話,甚至可能自動打碼或刪除其形象。樂昆指出,F(xiàn)acebook對這種工具非常感興趣,不過他也強調(diào),F(xiàn)acebook對機器學習的興趣要遠遠超出圖像識別本身。

????Facebook的目標是教會電腦學會識別人的情感。顯然電腦不可能擁有人類的感受,但人類可以教電腦識別感情以及人們對各種感情的反應。如果電腦達到了這種理解程度,那么如果你喝醉了酒,要上傳一張醉態(tài)照片的時候,F(xiàn)acebook可能就會提醒你是否真的想這樣做。

????“這將不是人臉識別技術(shù)”,樂昆表示:“我們不在乎照片里的人是誰。我們會使用其它類型的圖像識別技術(shù),然后以不同的方法訓練機器,比如說某張照片看起來非常尷尬,我們就會提醒你,確保你是真的想把這張照片公開到網(wǎng)上?!?/p>

????目前Facebook尚不具備這樣的技術(shù),樂昆也只是假設性地提出了這些概念,以介紹Facebook的人工智能技術(shù)會朝著什么方向發(fā)展。當然,這種高端的算法技術(shù)可能也會令人深感不適。目前Facebook在加拿大和歐盟各國沒有啟用自動標簽功能,就是出于隱私方面的考慮。另外,一想到你在打算上傳照片時,電腦還要替你再審查一遍,或是一想到你在發(fā)段子的時候,電腦正在努力理解你的笑點,這種感覺的確是令人渾身不舒服。

????樂昆表示:“我們希望讓機器變得更加智能,能夠理解文字、圖像、視頻和帖子??傊?,任何有可能發(fā)生在網(wǎng)絡世界的事情,我們都想了解其語境。”由于網(wǎng)上有太多的數(shù)碼內(nèi)容,人們的信息很容易被各種各樣的其它信息所淹沒。而樂昆的團隊則可以根據(jù)與人們的興趣和最關(guān)注的事情將他們聯(lián)系在一起。如此復雜的解決方案,只是為了實現(xiàn)一個簡單的目標:確保你在Facebook上能看到你想看的東西。

????樂昆表示:“這才是我們在Facebook想要實現(xiàn)的大目標,也就是讓機器理解人。”(財富中文網(wǎng))

????譯者:樸成奎

????審校: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.”

掃碼打開財富Plus App
尤物蜜芽视频在线观看国产| 99re视频热这里只有精品| ?愛妃?国产一区二区三区视频精品| 国产一区二区三区色婬影院| 国产亚洲曝欧美不卡精品| 色欲精品国产一区二区三区AV| 欧美精品久久天天躁_天堂8在线天堂资源BT| 亚洲国产日韩a在线播放| 欧美老妇交乱视频在线观看| 国产美女露脸口爆吞精一区二区| 久久香综合精品久久伊人| 亚洲中文字幕久久精品无码a| 人妻丰满熟妇AV无码区| 久久综合九色综合欧美就去吻中文字幕最新在线| 国产最爽的乱婬视频国语对白| 亚洲A∨精品一区二区三区| 777米奇影视第四色| 亚洲国产一区二区在线观看| 亚洲日本香蕉91视频| 精品人妻少妇嫩草AV无码专区| 欧美日韩影音先锋第一页| 人妻无码αv中文字幕久久| 吃下面吃胸在线看无码| 久久人爽人人爽人人片| 久久精品久久久久久久精品| 中韩高清无专码区2021曰| 五月精品亚洲婷婷| 女同ⅹxx女同les高潮视频| 人妻激情另类乱人伦人妻| 国产丝袜拍偷超清在线| 色综合婷婷在线观看66| 精品.18岁末年禁止欢观看在线a 日本一区二区在线看| 无码内射中文字幕岛国片| 国产亚洲精品无码拍拍拍| 秋霞2016午夜限制电影在线| 亚洲精品香蕉婷婷在线观看| 波多野结衣绝顶大高潮| 亚洲AV无码专区亚洲AV不卡| 无码人妻精品一区二区蜜桃网站| 免费无码婬片AAAA片直播表情| 成人 污污污在线观看|