好英語網好英語網

好英語網 - www.676827.live
好英語網一個提供英語閱讀,雙語閱讀,雙語新聞的英語學習網站。

16000臺電腦一起找貓

How Many Computers to Identify a Cat? 16,000
16000臺電腦一起找貓

MOUNTAIN VIEW, Calif. — Inside Google’s secretive X laboratory, known for inventing self-driving cars and augmented reality glasses, a small group of researchers began working several years ago on a simulation of the human brain.

加利福尼亞州山景城——“X實驗室”是谷歌的秘密實驗室,以發明無人駕駛汽車和增強現實眼鏡而聞名。幾年前,一個研究小組開始在這里研究仿真人腦。

There Google scientists created one of the largest neural networks for machine learning by connecting 16,000 computer processors, which they turned loose on the Internet to learn on its own.

在這里,谷歌的科學家們將16000個計算機處理器聯接起來,建造了一個超大規模的機器學習神經網絡。他們把這個網絡放置在互聯網上,任其自主學習。
 

一幅貓的圖像,神經網絡能夠自行對其進行識別。

Presented with 10 million digital images found in YouTube videos, what did Google’s brain do? What millions of humans do with YouTube: looked for cats.

面對YouTube視頻里的大約1000萬張數碼圖片,“谷歌大腦”能做些什么呢?他們要做的是成千上萬的人在YouTube上所做的事情:找貓。

The neural network taught itself to recognize cats, which is actually no frivolous activity. This week the researchers will present the results of their work at a conference in Edinburgh, Scotland. The Google scientists and programmers will note that while it is hardly news that the Internet is full of cat videos, the simulation nevertheless surprised them. It performed far better than any previous effort by roughly doubling its accuracy in recognizing objects in a challenging list of 20,000 distinct items.

這個神經網絡自主學習識別貓兒的方法, 說實在的,這可不是什么瑣碎無聊的舉動。本周,研究人員將在蘇格蘭愛丁堡的一次會議上展示自己的研究成果。谷歌科學家和程序設計員將會說明,雖然互聯網上充滿貓兒視頻的事情已經不再是什么新聞,模擬的結果還是讓他們大吃了一驚。這個系統在20000個不同物體里識別目標物的精確度大致上提高了一倍,遠遠高于以往的任何一次同類實驗。

The research is representative of a new generation of computer science that is exploiting the falling cost of computing and the availability of huge clusters of computers in giant data centers. It is leading to significant advances in areas as diverse as machine vision and perception, speech recognition and language translation.

新生代的計算機科學得益于計算成本的降低,以及在巨型數據中心使用大型計算機集群的可能性。這項研究便是其代表,將給機器視覺和知覺、語音辨識以及語言翻譯等諸多領域帶來重要進步。

Although some of the computer science ideas that the researchers are using are not new, the sheer scale of the software simulations is leading to learning systems that were not previously possible. And Google researchers are not alone in exploiting the techniques, which are referred to as “deep learning” models. Last year Microsoft scientists presented research showing that the techniques could be applied equally well to build computer systems to understand human speech.

雖然研究人員所使用的某些計算機科學概念以前就存在,此次軟件模擬卻擁有十分巨大的規模,足以構筑之前不可能實現的學習系統。利用此類科技的并非只有谷歌的研究人員,他們所做的研究被稱為“深度學習”模式。去年,微軟科學家所展示的研究成果表明,該科技也可以被用來建造能理解人類語言的計算機系統。

“This is the hottest thing in the speech recognition field these days,” said Yann LeCun, a computer scientist who specializes in machine learning at the Courant Institute of Mathematical Sciences at New York University.

在紐約大學庫蘭特數學科學研究所(the CourantInstitute ofMathematical Sciences at New York University)從事機器學習技術研究的計算機科學家嚴恩·勒坤(YannLeCun)說:“現在這是語音辨識領域最熱門的事。”

And then, of course, there are the cats.

當然,還有貓。

To find them, the Google research team, lead by the Stanford University computer scientist Andrew Y. Ng and the Google fellow Jeff Dean, used an array of 16,000 processors to create a neural network with more than one billion connections. They then fed it random thumbnails of images, one each extracted from 10 million YouTube videos.

為了找到貓,由斯坦福大學(StanfordUniversity)的計算機學家安德魯·吳(Andrew Y. Ng)和谷歌員工杰夫·迪安(Jeff Dean)領導的谷歌研究小組用16000個處理器建造了一個神經網絡,這個網絡有10億多個連接點。隨后,他們向這個系統隨機提供從1000萬個YouTube視頻中截取的縮略圖,每個視頻截取一張。

Currently much commercial machine vision technology is done by having humans “supervise” the learning process by labeling specific features. In the Google research, the machine was given no help in identifying features.

目前,多數商業機器視覺技術都是通過標注詳細特征,由人工“指導”學習過程來完成的。而在谷歌的此項研究中,機器在識別特征時未得到任何輔助。

“The idea is that instead of having teams of researchers trying to find out how to find edges, you instead throw a ton of data at the algorithm and you let the data speak and have the software automatically learn from the data,” Dr. Ng said.

吳說:“我們的理念就是,把大量數據交給算法去處理,然后讓數據自己說話,讓軟件自動從這些數據中學習,而不是由大量的研究人員去突破推進。”

“We never told it during the training, ‘This is a cat,’ ” said Dr. Dean, who originally helped Google design the software that lets it easily break programs into many tasks that can be computed simultaneously. “It basically invented the concept of a cat. We probably have other ones that are side views of cats.”

“在訓練中我們從未告訴過它,‘這就是貓,’”迪安說。最初,他幫谷歌設計了能輕松將程序集分解為多項任務的軟件,以便同時處理多個任務。“基本上是這個系統自主創造了‘貓’這個概念。系統甚至可能會找出貓的側影圖片。”

The Google brain assembled a dreamlike digital image of a cat by employing a hierarchy of memory locations to successively cull out general features after being exposed to millions of images. The scientists said, however, that it appeared they had developed a cybernetic cousin to what takes place in the brain’s visual cortex.

面對成千上萬張圖像,“谷歌大腦”使用了一組存儲單元,逐步篩選出貓的共同特征,合成了一張朦朧的數碼圖像。此外,科學家們表示,他們似乎創建了一個人工智能系統,功能與人腦視覺皮質中發生的活動類似。

Neuroscientists have discussed the possibility of what they call the “grandmother neuron,” specialized cells in the brain that fire when they are exposed repeatedly or “trained” to recognize a particular face of an individual.

神經系統科學家們還探討過制造所謂“祖母神經元”的可能性。這是人腦中的一些特化細胞,當某人的頭像反復出現,或者“訓練”它們識別某個頭像時,它們就會產生反應。

“You learn to identify a friend through repetition,” said Gary Bradski, a neuroscientist at Industrial Perception, in Palo Alto, Calif.

“只有通過不斷重復,你才能記得朋友的長相,”加利福尼亞州帕洛阿爾托“工業知覺”(IndustrialPerception神經系統科學家加里·布拉德斯基(Gary Bradski)說。

While the scientists were struck by the parallel emergence of the cat images, as well as human faces and body parts in specific memory regions of their computer model, Dr. Ng said he was cautious about drawing parallels between his software system and biological life.

計算機模型特定記憶區域里同時出現的貓圖像、人臉和人類身體部分讓科學家們十分震驚,但吳表示,他的態度比較謹慎,不會把這個軟件系統和生命體劃上等號。

“A loose and frankly awful analogy is that our numerical parameters correspond to synapses,” said Dr. Ng. He noted that one difference was that despite the immense computing capacity that the scientists used, it was still dwarfed by the number of connections found in the brain.

吳說:“有人把我們所設置的數值參數比成神經元上的突觸,這樣的類比是不太嚴密甚至可怕的。”他表示區別在于,盡管科學家們所使用的計算機處理能力很強大,但在人腦連接點的數量面前,它還是很微不足道。

“It is worth noting that our network is still tiny compared to the human visual cortex, which is 106 times larger in terms of the number of neurons and synapses,” the researchers wrote.

研究人員寫道:“值得注意的是,和人腦視覺皮質相比,我們的系統仍然渺小。人腦視覺皮質上的神經元和突觸的數量比它多出了106倍。”

Despite being dwarfed by the immense scale of biological brains, the Google research provides new evidence that existing machine learning algorithms improve greatly as the machines are given access to large pools of data.

雖然在生物大腦的龐大規模面前顯得渺小,谷歌的研究還是提供了新的證據,證明在給予機器海量數據之后,現有的機器學習算法可以得到極大的提高。

“The Stanford/Google paper pushes the envelope on the size and scale of neural networks by an order of magnitude over previous efforts,” said David A. Bader, executive director of high-performance computing at the Georgia Tech College of Computing. He said that rapid increases in computer technology would close the gap within a relatively short period of time: “The scale of modeling the full human visual cortex may be within reach before the end of the decade.”

佐治亞理工學院計算機系(Georgia Tech College ofComputing)高性能計算系統實驗室執行主任戴維·巴德(David A. Bader)表示:“和原來相比,斯坦福和谷歌的研究報告把神經網絡的規模上限提高了一個量級。”他說,計算機科技的迅速發展會在相對較短的時期內縮小電腦和人腦的差距。“在這個十年結束之前,整個兒地模擬人類視覺皮質也不是不可能的事情。”

Google scientists said that the research project had now moved out of the Google X laboratory and was being pursued in the division that houses the company’s search business and related services. Potential applications include improvements to image search, speech recognition and machine language translation.

谷歌的科學家表示,現在這一研究項目已經移出谷歌X實驗室,由負責搜索業務及相關服務的部門接手。未來可能的應用方向包括改進圖像搜索、語音識別和機器語言翻譯。

Despite their success, the Google researchers remained cautious about whether they had hit upon the holy grail of machines that can teach themselves.

盡管取得了這些成功,谷歌的科學家們仍然出言謹慎,不敢斷言自己已經拿到了機器自主學習技術的圣杯。

“It’d be fantastic if it turns out that all we need to do is take current algorithms and run them bigger, but my gut feeling is that we still don’t quite have the right algorithm yet,” said Dr. Ng.

吳說:“如果我們要做的只是采用現在的算法然后將其擴大,那就太棒了,但是直覺告訴我,我們還沒有找到正確的算法。”
贊一下
上一篇: 電子貨幣支付會導致花費更多嗎?
下一篇: 返回列表

相關推薦

隱藏邊欄
陕西快乐10分任4统计 海南天天麻将下载安 英超直播网站 宁夏11选5平台 喜迎棋牌怎么样 手机斗牛的棋牌游戏 鲁抗医药股票代码 喜迎棋牌游戏2018官方下载 天津11选五今天第45 二分彩计划走势图 辽宁11选5近100期走势图