循聲覓船計(jì)算機(jī)也用著招英語(yǔ)美文
In "The Hunt for Red October," the soviet submarine captain played by Sean Connery commands his crew to verify the location of a target.
在影片《獵殺紅色十月》中，肖恩·康納利扮演的蘇聯(lián)潛艇艦長(zhǎng)命令船員確認(rèn)目標(biāo)方位。(電影片段：“瓦西里，發(fā)個(gè)‘呯’聲，發(fā)一聲即可�！�)
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.
這種聲音就是所謂的主動(dòng)聲吶。海軍研究辦公室的鮑勃·海德利克表示，發(fā)出這種聲音與打開(kāi)手電筒無(wú)異，雖然會(huì)獲得信息，但是也向其他船只透露了自身位置。
"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.
“駕駛潛艇，保持航行路線不為人知是重中之重�！睗撏章�(tīng)推進(jìn)器和電子元件的聲音，監(jiān)聽(tīng)其他船只位置，保持行駛路線的隱秘性。以上方法又稱“被動(dòng)聲吶”，通常只有訓(xùn)練有素的操作員才能掌握。不過(guò)研究人員現(xiàn)在正在教授機(jī)器這項(xiàng)技術(shù)。
They first recorded the underwater rumblings of cargo ships off the California coast <> 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?
他們?cè)诩永Ｄ醽啚乘嫦掳惭b了28個(gè)麥克風(fēng)，記錄加利福尼亞灣貨船所發(fā)出的轟鳴聲。他們將這種聲音加入機(jī)器學(xué)習(xí)算法，然后為算法播放一段新錄音，并對(duì)其提問(wèn)：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.
斯克里普斯海洋研究所水中聲學(xué)專業(yè)博士生艾瑪·歐扎尼齊說(shuō)：“計(jì)算機(jī)算法表現(xiàn)得不錯(cuò)。”她表示，借助音頻數(shù)據(jù)，算法可在長(zhǎng)達(dá)10千米的距離中將船只方位限定在幾百米之內(nèi)。
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.
然而人們?nèi)圆磺宄䴔C(jī)器究竟學(xué)會(huì)了什么�！叭藗儼l(fā)現(xiàn)，機(jī)器學(xué)習(xí)，尤其是神經(jīng)網(wǎng)絡(luò)的具體學(xué)習(xí)內(nèi)容更加難以確定，這正是其耐人尋味的'原因之一，它與黑匣子有些許類似�！边@份研究報(bào)告發(fā)表在《美國(guó)聲學(xué)協(xié)會(huì)期刊》上。
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."
海軍研究辦公室的鮑勃·海德利克表示，相比于現(xiàn)實(shí)中潛艇需要解決的問(wèn)題，這些設(shè)定數(shù)據(jù)要相對(duì)簡(jiǎn)單一些。盡管如此，這也有了長(zhǎng)足進(jìn)步：“人們可以絞盡腦汁，設(shè)想自己設(shè)計(jì)出一種電腦程序，足以擊敗訓(xùn)練有素的專業(yè)人士�！�
There is a precedent, after all, for machines defeating our best human operators. It was in that other great battle of the Cold War: the game of chess.
畢竟機(jī)器在特定領(lǐng)域戰(zhàn)勝人類早有先例，而該領(lǐng)域正是冷戰(zhàn)時(shí)期另一大戰(zhàn)場(chǎng)：國(guó)際象棋。
【循聲覓船計(jì)算機(jī)也用著招英語(yǔ)美文】相關(guān)文章：
窮人也浪漫英語(yǔ)美文07-18
覓春英語(yǔ)作文03-26
招中招經(jīng)典美文06-08
夏日溯溪覓清涼寫景美文08-27
也說(shuō)父親的美文03-22
也談責(zé)任美文12-10
愛(ài)情也需要尊重的美文02-07
接受也很高貴的美文06-07