In The Hunt for Red October, the Soviet submarine captain played by Sean Connery commands his crew to verify the location of a target. <<MOVIE CLIP: "Give me a ping Vasily. One ping only please.">>

　　在電影《獵殺紅色十月號》（1990年美國電影）中，演員Sean Connery扮演的前蘇聯(lián)潛艇艇長(cháng)指揮手下確定一個(gè)目標的位置時(shí)說(shuō)：“Vasily，請發(fā)射一個(gè)聲脈沖信號，只要一個(gè)！”

　　That ping is known as "active sonar." Bob Headrick of the Office of Naval Research, the ONR, says it's the audio equivalent of switching on a flashlight. You're getting information, but also broadcasting your location to other ships.

　　艇長(cháng)說(shuō)的聲脈沖信號就是“主動(dòng)聲納”。美國海軍研究辦公室（ONR）的Bob Headrick說(shuō)，這相當于打開(kāi)一個(gè)手電筒，你在獲取他人信息的同時(shí)也泄露了自己的位置。

　　"And you know the number one priority in the submarine is to remain undetected." Subs can keep their secrecy by eavesdropping on other ships instead… listening for propellers and electronics and so on. Such methods, known as "passive sonar,” generally require a skilled operator. But researchers are teaching machines to do it, too.

　　“你知道，潛艇的首要任務(wù)是保持隱身，不被發(fā)現。”潛艇通過(guò)偵聽(tīng)其他艦船的聲音—如螺旋槳、電子設備的噪聲--來(lái)保護自己的秘密位置。這種方法叫做“被動(dòng)聲納”，通常需要配備一名技能熟練的操作員。但研究人員正在教計算機做這件事。

　　They first recorded the underwater rumblings of cargo ships off the California coast <<ship sound>> using an array of 28 underwater microphones. They fed that sound, along with the ships' actual GPS coordinates, to their machine learning algorithms. And then they gave the algorithms new recordings, and asked: where's the ship?

　　研究人員首先搭建了28個(gè)水聽(tīng)器組成的傳感器陣，記錄加利福尼亞海岸過(guò)往船只發(fā)出的隆隆聲，并將這些聲音信號和船只的實(shí)際GPS坐標“喂給”機器學(xué)習算法。給算法一些新的船只噪音，然后向它提問(wèn)：現在船在哪里？

　　"And it did extremely well." Emma Ozanich, a PhD Student in underwater acoustics at the Scripps Institution of Oceanography. Using the audio data, she says the algorithms pinpointed the ships to within a couple hundred meters, at distances of up to 10 kilometers.

　　斯克利普斯海洋研究所水聲專(zhuān)業(yè)的博士生Emma Ozanich認為“計算機做得非常好”。利用噪音數據，機器學(xué)習算法可以在長(cháng)達10公里距離的范圍里定位船只，誤差在兩三百米以?xún)取?/p>

　　But it's not so clear what the machines now know. "One of the interesting parts about machine learning, especially neural networks, is that it's more difficult to pull out what it's actually learning specifically. It's a little bit of a black box." The research is in The Journal of the Acoustical Society of America. [Haiqiang Niu et al., Ship localization in Santa Barbara Channel using machine learning classifiers]

　　但人們還不清楚機器目前知道哪些信息。“機器學(xué)習特別是神經(jīng)網(wǎng)絡(luò )有趣的一個(gè)部分是很難把它具體學(xué)習的東西提取出來(lái)，這有點(diǎn)像是一個(gè)黑匣子。”研究成果近日發(fā)表于美國聲學(xué)學(xué)報（牛海強等人，2017年11月）。

　　Bob Headrick of ONR says the data set used here is relatively simple, compared to the real-world scenarios subs would have to solve. Still, he says, with lots more development: "You could conceive with enough effort you create the computer program that can beat the trained operator."

　　ONR的Bob Headrick指出，與潛艇需要解決的實(shí)際問(wèn)題相比，本次研究使用的數據相對簡(jiǎn)單，但隨著(zhù)進(jìn)一步的發(fā)展，“你可以通過(guò)努力，研發(fā)出一個(gè)能打敗訓練有素的操作員的計算機程序。”

　　There is a precedent, after all, for machines defeating our best human operators. It was in that other great battle: the game of chess.

　　畢竟機器打敗最聰明人類(lèi)已有先例。那是另一場(chǎng)戰役：國際象棋。（編輯注：1997年人機象棋大賽，IBM電腦“深藍”打敗了當時(shí)的世界棋王卡斯帕羅夫。）

　　來(lái)源：科學(xué)美國人專(zhuān)欄《科學(xué)60秒》

　　作者：Christopher Intagliata

　　編輯/翻譯：王榮泉

　　校對：牛海強

　　報道原文：

　　Computers Learn to Use Sound to Find Ships - Scientific American https://www.scientificamerican.com/podcast/episode/computers-learn-to-use-sound-to-find-ships/

　　牛海強論文：

　　Ship localization in Santa Barbara Channel using machine learning classifiers

　　http://asa.scitation.org/doi/abs/10.1121/1.5010064