[新聞] 以繞射取代電子的3D列印深度學習神經網路已回收
1.媒體來源: New Atlas
2.完整新聞標題:
3D-printed Deep Learning neural network uses light instead of electrons
以光學繞射取代電子的3D列印深度學習神經網路
3.完整新聞內文:
Matt Kennedy
August 1st, 2018
It's a novel idea, using light diffracted through numerous plates instead of
electrons. And to some, it might seem a little like replacing a computer with
an abacus, but researchers at UCLA have high hopes for their quirky, shiny,
speed-of-light artificial neural network.
利用光線穿透數個薄板產生的繞射來取代電子是個新奇的概念。一些人可能會認為這有點
像是用算盤來代替電腦,但UCLA的研究人員對這個古怪、閃亮、光速的人工神經網路寄予
厚望。
Coined by Rina Dechter in 1986, Deep Learning is one of the fastest-growing
methodologies in the machine learning community and is often used in face,
speech and audio recognition, language processing, social network filtering
and medical image analysis as well as addressing more specific tasks, such as
solving inverse imaging problems.
1986年 Rina Dechter 發明的深度學習是機器學習領域中發展得最快的方法之一,它經常
用於臉部、語音、聲音辨識、語言處理、社群網路篩選與醫學影像分析,以及更特殊的任
務,例如解決逆成像問題。
Traditionally, deep learning systems are implemented on a computer to learn
data representation and abstraction and perform tasks, on par with – or
better than – the performance of humans. However the team led by Dr. Aydogan
Ozcan, the Chancellor's Professor of electrical and computer engineering at
UCLA, didn't use a traditional computer set-up, instead choosing to forgo all
those energy-hungry electrons in favor of light waves. The result was its
all-optical Diffractive Deep Neural Network (D2NN) architecture.
傳統上,是在電腦中建立深度學習系統來學習並執行任務,執行任務的表現與人類相當或
更好。然而UCLA電機電腦工程教授 Aydogan Ozcan 帶領的團隊並沒有使用傳統的電腦,
他們放棄那些耗能的電子裝置改而選擇光波。最後的成果就是全光學繞射深度神經網路
(D2NN)。
https://i.imgur.com/8cd5Czh.jpg
The setup uses 3D-printed translucent sheets, each with thousands of raised
pixels, which deflect light through each panel in order to perform set tasks.
By the way, these tasks are performed without the use of any power, except
for the input light beam.
這個裝置使用3D列印的半透明薄片,每張薄片上有許多凸起的像素,這些像素改變穿過薄
片的光路以執行任務。另外,除了輸入的光束,整個過程不需要任何能量。
The UCLA team's all-optical deep neural network – which looks like the guts
of a solid gold car battery – literally operates at the speed of light, and
will find applications in image analysis, feature detection and object
classification. Researchers on the team also envisage possibilities for D2NN
architectures performing specialized tasks in cameras. Perhaps your next DSLR
might identify your subjects on the fly and post the tagged image to your
Facebook timeline.
UCLA團隊的全光學繞射深度神經網路 — 看起來像金色的汽車電池內部 — 實際上以光速
運行,並且將在圖像分析、特徵檢測與物件分類中找到應用。研究人員也設想了D2NN架構
在照相機中執行專門任務的可能性。也許你的下一個數位單眼相機就會動態識別拍攝的主
體並且上傳標記好的圖像到 Facebook 的動態時報。
https://i.imgur.com/5EaigPx.jpg
"Using passive components that are fabricated layer by layer, and connecting
these layers to each other via light diffraction created a unique all-optical
platform to perform machine learning tasks at the speed of light," said Dr.
Ozcan.
Ozcan 表示:「使用逐層製造的被動元件,經由光繞射將這些層相互連結,創造出一個獨
特的全光學平台,以光速執行機器學習任務」。
For now though, this is a proof of concept, but it shines a light on some
unique opportunities for the machine learning industry.
就目前而言,這是一個概念驗證,但它為機器學習行業提供了一些獨特的機會。
The research has been published in the journal Science.
該研究發表在《科學》期刊上。
Source: The Ozcan Research Group
4.完整新聞連結 (或短網址):
https://newatlas.com/diffractive-deep-neural-network-uses-light-to-learn/55718/
5.備註:
學習(訓練)過程應該還是要靠電腦,等學成後就可以印出來靠光學繞射執行任務。
--
※ 發信站: 批踢踢實業坊(ptt.cc), 來自: 36.230.48.139
※ 文章網址: https://www.ptt.cc/bbs/Gossiping/M.1533385181.A.9BF.html
→
08/04 20:20,
5年前
, 1F
08/04 20:20, 1F
推
08/04 20:20,
5年前
, 2F
08/04 20:20, 2F
推
08/04 20:20,
5年前
, 3F
08/04 20:20, 3F
→
08/04 20:20,
5年前
, 4F
08/04 20:20, 4F
推
08/04 20:21,
5年前
, 5F
08/04 20:21, 5F
推
08/04 20:21,
5年前
, 6F
08/04 20:21, 6F
噓
08/04 20:22,
5年前
, 7F
08/04 20:22, 7F
推
08/04 20:22,
5年前
, 8F
08/04 20:22, 8F
→
08/04 20:23,
5年前
, 9F
08/04 20:23, 9F
推
08/04 20:23,
5年前
, 10F
08/04 20:23, 10F
推
08/04 20:24,
5年前
, 11F
08/04 20:24, 11F
→
08/04 20:24,
5年前
, 12F
08/04 20:24, 12F
→
08/04 20:24,
5年前
, 13F
08/04 20:24, 13F
※ 編輯: JKLee (36.230.48.139), 08/04/2018 20:25:44
推
08/04 20:25,
5年前
, 14F
08/04 20:25, 14F
推
08/04 20:26,
5年前
, 15F
08/04 20:26, 15F
推
08/04 20:28,
5年前
, 16F
08/04 20:28, 16F
→
08/04 20:35,
5年前
, 17F
08/04 20:35, 17F
→
08/04 20:35,
5年前
, 18F
08/04 20:35, 18F
→
08/04 20:35,
5年前
, 19F
08/04 20:35, 19F
→
08/04 20:35,
5年前
, 20F
08/04 20:35, 20F
推
08/04 20:36,
5年前
, 21F
08/04 20:36, 21F
推
08/04 20:38,
5年前
, 22F
08/04 20:38, 22F
→
08/04 20:43,
5年前
, 23F
08/04 20:43, 23F
推
08/04 20:47,
5年前
, 24F
08/04 20:47, 24F
推
08/04 20:50,
5年前
, 25F
08/04 20:50, 25F
→
08/04 20:50,
5年前
, 26F
08/04 20:50, 26F
推
08/04 20:51,
5年前
, 27F
08/04 20:51, 27F
→
08/04 20:51,
5年前
, 28F
08/04 20:51, 28F
→
08/04 20:51,
5年前
, 29F
08/04 20:51, 29F
→
08/04 20:52,
5年前
, 30F
08/04 20:52, 30F
→
08/04 20:53,
5年前
, 31F
08/04 20:53, 31F
推
08/04 21:05,
5年前
, 32F
08/04 21:05, 32F
推
08/04 21:15,
5年前
, 33F
08/04 21:15, 33F
推
08/04 21:16,
5年前
, 34F
08/04 21:16, 34F
推
08/04 21:23,
5年前
, 35F
08/04 21:23, 35F
推
08/04 21:28,
5年前
, 36F
08/04 21:28, 36F
→
08/04 21:28,
5年前
, 37F
08/04 21:28, 37F
推
08/04 21:40,
5年前
, 38F
08/04 21:40, 38F
→
08/04 22:03,
5年前
, 39F
08/04 22:03, 39F
噓
08/04 22:07,
5年前
, 40F
08/04 22:07, 40F
可以指出我的錯誤在哪裡嗎?
※ 編輯: JKLee (36.230.48.139), 08/04/2018 22:12:45
推
08/04 22:28,
5年前
, 41F
08/04 22:28, 41F
推
08/04 22:40,
5年前
, 42F
08/04 22:40, 42F
推
08/04 23:03,
5年前
, 43F
08/04 23:03, 43F
推
08/05 00:59,
5年前
, 44F
08/05 00:59, 44F
→
08/05 00:59,
5年前
, 45F
08/05 00:59, 45F
→
08/05 00:59,
5年前
, 46F
08/05 00:59, 46F
推
08/05 01:13,
5年前
, 47F
08/05 01:13, 47F
→
08/05 01:14,
5年前
, 48F
08/05 01:14, 48F
→
08/05 01:34,
5年前
, 49F
08/05 01:34, 49F
→
08/05 01:34,
5年前
, 50F
08/05 01:34, 50F
→
08/05 01:34,
5年前
, 51F
08/05 01:34, 51F
→
08/05 01:34,
5年前
, 52F
08/05 01:34, 52F
推
08/05 02:09,
5年前
, 53F
08/05 02:09, 53F
→
08/05 02:11,
5年前
, 54F
08/05 02:11, 54F
→
08/05 02:13,
5年前
, 55F
08/05 02:13, 55F
→
08/05 02:13,
5年前
, 56F
08/05 02:13, 56F
推
08/05 03:22,
5年前
, 57F
08/05 03:22, 57F
→
08/05 03:22,
5年前
, 58F
08/05 03:22, 58F
推
08/05 08:01,
5年前
, 59F
08/05 08:01, 59F
推
08/05 09:13,
5年前
, 60F
08/05 09:13, 60F
推
08/05 10:56,
5年前
, 61F
08/05 10:56, 61F
討論串 (同標題文章)
以下文章回應了本文:
完整討論串 (本文為第 1 之 3 篇):