TED@BCG Paris
Blaise Agüera y Arcas: How computers are learning to be creative
布雷斯．阿規耶拉．雅克斯: 電腦是如何學會創意的？
Filmed:
Readability: 4.4
1,934,067 views
我們正站在藝術與創意時代的尖端——但不是人類做的。Google的首席科學家，布雷斯．阿規耶拉．雅克斯（Blaise Agüera y Arcas）運用深度神經網路，讓機械感知並呈現學習的成果。在這場迷人的演示中，他向我們展示如何訓練神經網路辨識圖片，以及如何反向操作讓電腦自行創造出畫作來。成果是：透過定義分類的方式，呈現出完美、迷幻的拼貼畫（及詩詞！）「感知與創造力是緊密相連的」。他說，「任何可以做出感知活動的生物、生命都能被創作出來」。
Blaise Agüera y Arcas - Software architect
Blaise Agüera y Arcas works on machine learning at Google. Previously a Distinguished Engineer at Microsoft, he has worked on augmented reality, mapping, wearable computing and natural user interfaces. Full bio
Blaise Agüera y Arcas works on machine learning at Google. Previously a Distinguished Engineer at Microsoft, he has worked on augmented reality, mapping, wearable computing and natural user interfaces. Full bio
Double-click the English transcript below to play the video.
00:12
So, I lead a team at Google
that works on machine intelligence;
that works on machine intelligence;
0
800
3124
我在 Google 帶領
一個團隊做機械智慧；
一個團隊做機械智慧；
00:15
in other words, the engineering discipline
of making computers and devices
of making computers and devices
1
3948
4650
換句話說，就是制定一些訓練方法，
00:20
able to do some of the things
that brains do.
that brains do.
2
8622
2419
讓電腦和裝置能做些大腦做的事。
00:23
And this makes us
interested in real brains
interested in real brains
3
11439
3099
而這也讓我們對真實的大腦
00:26
and neuroscience as well,
4
14562
1289
以及神經科學產生了興趣，
00:27
and especially interested
in the things that our brains do
in the things that our brains do
5
15875
4172
特別是一些我們大腦能做
00:32
that are still far superior
to the performance of computers.
to the performance of computers.
6
20071
4042
但電腦仍無法呈現出來的事。
00:37
Historically, one of those areas
has been perception,
has been perception,
7
25209
3609
長期以來，機械智慧的
其中一個領域談的就是機械感知，
其中一個領域談的就是機械感知，
00:40
the process by which things
out there in the world --
out there in the world --
8
28842
3039
它是一種轉化的過程——
00:43
sounds and images --
9
31905
1584
像是把聲音和影像——
00:45
can turn into concepts in the mind.
10
33513
2178
轉化成心智上的概念。
00:48
This is essential for our own brains,
11
36235
2517
這是我們大腦必備的能力，
00:50
and it's also pretty useful on a computer.
12
38776
2464
這個能力對電腦來說也很有用。
00:53
The machine perception algorithms,
for example, that our team makes,
for example, that our team makes,
13
41636
3350
所謂的機械感知演算法，
像是我們團隊做的，
像是我們團隊做的，
00:57
are what enable your pictures
on Google Photos to become searchable,
on Google Photos to become searchable,
14
45010
3874
能讓你 Google 相簿裡的照片
01:00
based on what's in them.
15
48908
1397
根據照片裡的東西
把它們變成可以被搜尋的資料。
把它們變成可以被搜尋的資料。
01:03
The flip side of perception is creativity:
16
51594
3493
感知的另一面是創意：
01:07
turning a concept into something
out there into the world.
out there into the world.
17
55111
3038
把概念轉化成另一種東西。
01:10
So over the past year,
our work on machine perception
our work on machine perception
18
58173
3555
所以過去幾年，
我們團隊在機器感知上的努力，
我們團隊在機器感知上的努力，
01:13
has also unexpectedly connected
with the world of machine creativity
with the world of machine creativity
19
61752
4859
已經可以把創意與
機器藝術結合在一起。
01:18
and machine art.
20
66635
1160
01:20
I think Michelangelo
had a penetrating insight
had a penetrating insight
21
68556
3284
我覺得米開朗基羅對「感知」
與「創意」這兩者之間的關係
與「創意」這兩者之間的關係
01:23
into to this dual relationship
between perception and creativity.
between perception and creativity.
22
71864
3656
有一種很透析的看法。
01:28
This is a famous quote of his:
23
76023
2006
他有一句名言：
01:30
"Every block of stone
has a statue inside of it,
has a statue inside of it,
24
78053
3323
「每一塊石頭裡都藏著一座雕像，
01:34
and the job of the sculptor
is to discover it."
is to discover it."
25
82036
3002
等待雕刻家將它雕塑出來。」
01:38
So I think that what
Michelangelo was getting at
Michelangelo was getting at
26
86029
3216
所以我覺得米開朗基羅
當時的體悟是：
當時的體悟是：
01:41
is that we create by perceiving,
27
89269
3180
我們的「創意」來自「感知」，
01:44
and that perception itself
is an act of imagination
is an act of imagination
28
92473
3023
而感知本身就是一個想像行為
01:47
and is the stuff of creativity.
29
95520
2461
及創意的來源。
01:50
The organ that does all the thinking
and perceiving and imagining,
and perceiving and imagining,
30
98691
3925
人體中有一個器官
能做出思考、感受和想像，
能做出思考、感受和想像，
01:54
of course, is the brain.
31
102640
1588
當然，那就是我們的大腦。
01:57
And I'd like to begin
with a brief bit of history
with a brief bit of history
32
105089
2545
我想先簡單地來談一談
01:59
about what we know about brains.
33
107658
2302
我們對大腦認知的歷史。
02:02
Because unlike, say,
the heart or the intestines,
the heart or the intestines,
34
110496
2446
因為大腦不像我們的心臟或腸道，
02:04
you really can't say very much
about a brain by just looking at it,
about a brain by just looking at it,
35
112966
3144
你不能光用看的來瞭解大腦，
02:08
at least with the naked eye.
36
116134
1412
光靠肉眼根本看不出個所以然來。
02:09
The early anatomists who looked at brains
37
117983
2416
早期研究大腦的解剖學家，
02:12
gave the superficial structures
of this thing all kinds of fanciful names,
of this thing all kinds of fanciful names,
38
120423
3807
在大腦表皮結構上
取了許多稀奇古怪的名字，
取了許多稀奇古怪的名字，
02:16
like hippocampus, meaning "little shrimp."
39
124254
2433
例如海馬體，意思是「小蝦子」。
02:18
But of course that sort of thing
doesn't tell us very much
doesn't tell us very much
40
126711
2764
當然，這樣的命名方式
並沒有讓我們對
大腦的認識有太多的幫助。
大腦的認識有太多的幫助。
02:21
about what's actually going on inside.
41
129499
2318
02:24
The first person who, I think, really
developed some kind of insight
developed some kind of insight
42
132780
3613
我認為，第一個有真正深入了解
02:28
into what was going on in the brain
43
136417
1930
大腦如何運作的，
02:30
was the great Spanish neuroanatomist,
Santiago Ramón y Cajal,
Santiago Ramón y Cajal,
44
138371
3920
是偉大的西班牙神經解剖學家
桑地牙哥·拉蒙卡哈，
桑地牙哥·拉蒙卡哈，
02:34
in the 19th century,
45
142315
1544
他在十九世紀，
02:35
who used microscopy and special stains
46
143883
3755
就已經開始用顯微鏡和特殊染劑
02:39
that could selectively fill in
or render in very high contrast
or render in very high contrast
47
147662
4170
把大腦裡的特定細胞篩選出來染色，
02:43
the individual cells in the brain,
48
151856
2008
或以強烈的對比色來觀察細胞，
02:45
in order to start to understand
their morphologies.
their morphologies.
49
153888
3154
這樣做，是為了瞭解
它們的形態結構。
它們的形態結構。
02:49
And these are the kinds of drawings
that he made of neurons
that he made of neurons
50
157972
2891
這些是他在十九世紀時
02:52
in the 19th century.
51
160887
1209
畫的神經細胞圖，
02:54
This is from a bird brain.
52
162120
1884
這一張是鳥的大腦。
02:56
And you see this incredible variety
of different sorts of cells,
of different sorts of cells,
53
164028
3057
但當時已經可以看到
各式各樣不同的細胞圖片，
各式各樣不同的細胞圖片，
02:59
even the cellular theory itself
was quite new at this point.
was quite new at this point.
54
167109
3435
即使細胞的原理
在當時是個相當新穎的概念。
在當時是個相當新穎的概念。
03:02
And these structures,
55
170568
1278
這些結構，
03:03
these cells that have these arborizations,
56
171870
2259
這些樹枝狀的細胞結構，
03:06
these branches that can go
very, very long distances --
very, very long distances --
57
174153
2608
可以延伸到相當相當長──
03:08
this was very novel at the time.
58
176785
1616
在當時來講，
這樣的發現算是相當神奇了。
這樣的發現算是相當神奇了。
03:10
They're reminiscent, of course, of wires.
59
178779
2903
當然，它們也會讓人聯想到電線，
03:13
That might have been obvious
to some people in the 19th century;
to some people in the 19th century;
60
181706
3457
這對 19 世紀的人來說，
這樣的比喻可能比較恰當，
這樣的比喻可能比較恰當，
03:17
the revolutions of wiring and electricity
were just getting underway.
were just getting underway.
61
185187
4314
因為當時電線和電力的變革
正如火如荼的進行。
正如火如荼的進行。
03:21
But in many ways,
62
189964
1178
但就很多方面來說，
03:23
these microanatomical drawings
of Ramón y Cajal's, like this one,
of Ramón y Cajal's, like this one,
63
191166
3313
像拉蒙卡哈這樣的顯微鏡解剖圖
03:26
they're still in some ways unsurpassed.
64
194503
2332
現在看來還是很厲害。
03:28
We're still more than a century later,
65
196859
1854
但我們卻在一個世紀後，
03:30
trying to finish the job
that Ramón y Cajal started.
that Ramón y Cajal started.
66
198737
2825
才想試著去完成
當年拉蒙卡哈的研究。
當年拉蒙卡哈的研究。
03:33
These are raw data from our collaborators
67
201586
3134
這些原始資料，來自我們
03:36
at the Max Planck Institute
of Neuroscience.
of Neuroscience.
68
204744
2881
馬克斯·普朗克
神經科學機構的合作夥伴。
神經科學機構的合作夥伴。
03:39
And what our collaborators have done
69
207649
1790
而我們的合作夥伴的工作就是
03:41
is to image little pieces of brain tissue.
70
209463
5001
把大腦組織切成
一小片一小片的圖像。
一小片一小片的圖像。
03:46
The entire sample here
is about one cubic millimeter in size,
is about one cubic millimeter in size,
71
214488
3326
整個樣本的大小
大約只有 1 立方毫米，
大約只有 1 立方毫米，
03:49
and I'm showing you a very,
very small piece of it here.
very small piece of it here.
72
217838
2621
我展示給各位看的只有小小的一片。
03:52
That bar on the left is about one micron.
73
220483
2346
你可以看到，
左邊的長度標誌僅有一微米。
左邊的長度標誌僅有一微米。
03:54
The structures you see are mitochondria
74
222853
2409
各位現在看到的結構是粒線體，
03:57
that are the size of bacteria.
75
225286
2044
大小跟細菌一樣。
03:59
And these are consecutive slices
76
227354
1551
這些連續切片圖，
04:00
through this very, very
tiny block of tissue.
tiny block of tissue.
77
228929
3148
是由一塊很小的組織中
一片片切出來的。
一片片切出來的。
04:04
Just for comparison's sake,
78
232101
2403
舉個例子做比較，
04:06
the diameter of an average strand
of hair is about 100 microns.
of hair is about 100 microns.
79
234528
3792
一根頭髮的直徑
大約有 100 微米。
大約有 100 微米。
04:10
So we're looking at something
much, much smaller
much, much smaller
80
238344
2274
我們在研究的
是比一根頭髮還更細更小的東西。
04:12
than a single strand of hair.
81
240642
1398
04:14
And from these kinds of serial
electron microscopy slices,
electron microscopy slices,
82
242064
4031
而這一系列的電子顯微鏡切片圖像，
04:18
one can start to make reconstructions
in 3D of neurons that look like these.
in 3D of neurons that look like these.
83
246119
5008
可以組成像這樣的
神經元 3D 立體成像。
神經元 3D 立體成像。
04:23
So these are sort of in the same
style as Ramón y Cajal.
style as Ramón y Cajal.
84
251151
3157
這些和拉蒙卡哈
當年的研究相去不遠。
當年的研究相去不遠。
04:26
Only a few neurons lit up,
85
254332
1492
但只有幾個神經元可以打光，
04:27
because otherwise we wouldn't
be able to see anything here.
be able to see anything here.
86
255848
2781
否則我們會看不到東西。
04:30
It would be so crowded,
87
258653
1312
因為空間太壅擠、
04:31
so full of structure,
88
259989
1330
結構太複雜了，
04:33
of wiring all connecting
one neuron to another.
one neuron to another.
89
261343
2724
神經元蜿蜒地一個接著一個。
04:37
So Ramón y Cajal was a little bit
ahead of his time,
ahead of his time,
90
265293
2804
所以，拉蒙卡哈在當時
也算是走在時代的尖端，
也算是走在時代的尖端，
04:40
and progress on understanding the brain
91
268121
2555
但在那之後的幾十年，
04:42
proceeded slowly
over the next few decades.
over the next few decades.
92
270700
2271
人類對大腦的認識卻相當緩慢。
04:45
But we knew that neurons used electricity,
93
273455
2853
但我們已經知道
神經元是利用電子傳遞訊號，
神經元是利用電子傳遞訊號，
04:48
and by World War II, our technology
was advanced enough
was advanced enough
94
276332
2936
到第二次世界大戰前，
我們的科技已經進步到
我們的科技已經進步到
04:51
to start doing real electrical
experiments on live neurons
experiments on live neurons
95
279292
2806
可以在活體神經元上做電子實驗，
04:54
to better understand how they worked.
96
282122
2106
用來更好地理解它們是如何運作的。
04:56
This was the very same time
when computers were being invented,
when computers were being invented,
97
284631
4356
這也是電腦被發明出來的時間，
05:01
very much based on the idea
of modeling the brain --
of modeling the brain --
98
289011
3100
當初有一個模擬人腦的基礎想法——
05:04
of "intelligent machinery,"
as Alan Turing called it,
as Alan Turing called it,
99
292135
3085
是由艾倫·圖靈所提出，
他稱之為「智能機械」，
他稱之為「智能機械」，
05:07
one of the fathers of computer science.
100
295244
1991
他是計算機科學之父之一。
05:09
Warren McCulloch and Walter Pitts
looked at Ramón y Cajal's drawing
looked at Ramón y Cajal's drawing
101
297923
4632
當時沃倫麥卡洛克和華特彼特斯
（人工神經科學家）
（人工神經科學家）
05:14
of visual cortex,
102
302579
1317
看到的視覺皮質圖，
05:15
which I'm showing here.
103
303920
1562
就是上面這張拉蒙卡哈的圖片。
05:17
This is the cortex that processes
imagery that comes from the eye.
imagery that comes from the eye.
104
305506
4442
這個皮質層是負責把
眼睛傳來的訊號轉換成圖像。
眼睛傳來的訊號轉換成圖像。
05:22
And for them, this looked
like a circuit diagram.
like a circuit diagram.
105
310424
3508
他們當時發現，
它看起來像是一張電路圖。
它看起來像是一張電路圖。
05:26
So there are a lot of details
in McCulloch and Pitts's circuit diagram
in McCulloch and Pitts's circuit diagram
106
314353
3835
雖然麥卡洛克和彼特斯
在電路圖上有很多細節不太正確，
05:30
that are not quite right.
107
318212
1352
05:31
But this basic idea
108
319588
1235
但這樣的基礎概念，
05:32
that visual cortex works like a series
of computational elements
of computational elements
109
320847
3992
視覺皮層的工作原理
05:36
that pass information
one to the next in a cascade,
one to the next in a cascade,
110
324863
2746
像一系列的計算子
在串聯的電路圖上傳遞著資訊，
在串聯的電路圖上傳遞著資訊，
05:39
is essentially correct.
111
327633
1602
這樣的概念卻是相當正確的。
05:41
Let's talk for a moment
112
329259
2350
我們稍微聊一下，
05:43
about what a model for processing
visual information would need to do.
visual information would need to do.
113
331633
4032
產生視覺資訊的模型，
需要做哪些事情。
需要做哪些事情。
05:48
The basic task of perception
114
336228
2741
覺察力的基本任務就是
05:50
is to take an image like this one and say,
115
338993
4194
比如說，看到這一張圖片，
就要會判斷出，「這是一隻鳥」，
05:55
"That's a bird,"
116
343211
1176
05:56
which is a very simple thing
for us to do with our brains.
for us to do with our brains.
117
344411
2874
這對我們大腦來說是很簡單的任務。
05:59
But you should all understand
that for a computer,
that for a computer,
118
347309
3421
但各位要知道，這對電腦來說
06:02
this was pretty much impossible
just a few years ago.
just a few years ago.
119
350754
3087
在幾年前根本是不可能的事。
06:05
The classical computing paradigm
120
353865
1916
傳統的計算模式
06:07
is not one in which
this task is easy to do.
this task is easy to do.
121
355805
2507
根本不太容易跑出來這樣的任務。
06:11
So what's going on between the pixels,
122
359366
2552
所以，像素、
06:13
between the image of the bird
and the word "bird,"
and the word "bird,"
123
361942
4028
鳥圖與文字之間，
06:17
is essentially a set of neurons
connected to each other
connected to each other
124
365994
2814
一定要有一組彼此連結的神經元
在神經網路內相互作用著，
06:20
in a neural network,
125
368832
1155
06:22
as I'm diagramming here.
126
370011
1223
就像我這張示意圖。
06:23
This neural network could be biological,
inside our visual cortices,
inside our visual cortices,
127
371258
3272
這張神經網路圖
就像我們的視覺皮質運作原理。
就像我們的視覺皮質運作原理。
06:26
or, nowadays, we start
to have the capability
to have the capability
128
374554
2162
如今，我們已經有能力
06:28
to model such neural networks
on the computer.
on the computer.
129
376740
2454
用電腦來模擬這樣的神經網路。
06:31
And I'll show you what
that actually looks like.
that actually looks like.
130
379834
2353
接下來我向各位展示一下，
實際的操作大概是怎樣。
實際的操作大概是怎樣。
06:34
So the pixels you can think
about as a first layer of neurons,
about as a first layer of neurons,
131
382211
3416
圖片的像素你可以把它想像成是
第一層的神經元，
第一層的神經元，
06:37
and that's, in fact,
how it works in the eye --
how it works in the eye --
132
385651
2239
實際上，就是眼睛裡面
像素的呈現方式，
像素的呈現方式，
06:39
that's the neurons in the retina.
133
387914
1663
像素是透過
視網膜上的神經元做傳遞。
視網膜上的神經元做傳遞。
06:41
And those feed forward
134
389601
1500
而這些前饋資訊
06:43
into one layer after another layer,
after another layer of neurons,
after another layer of neurons,
135
391125
3403
會一層一層地傳遞到下一層神經元，
06:46
all connected by synapses
of different weights.
of different weights.
136
394552
3033
全部由不同的「突觸權重」所連結。
06:49
The behavior of this network
137
397609
1335
神經網路的行為
06:50
is characterized by the strengths
of all of those synapses.
of all of those synapses.
138
398968
3284
全都由這些突觸的強度所控制。
06:54
Those characterize the computational
properties of this network.
properties of this network.
139
402276
3288
它們決定了神經網路的計算模式。
06:57
And at the end of the day,
140
405588
1470
最後，
06:59
you have a neuron
or a small group of neurons
or a small group of neurons
141
407082
2447
會有一個或一小群的
神經元發出訊號，
神經元發出訊號，
07:01
that light up, saying, "bird."
142
409553
1647
辨識出該圖片就是，「鳥」。
07:03
Now I'm going to represent
those three things --
those three things --
143
411824
3132
我現在要來解釋一下這三個元素——
07:06
the input pixels and the synapses
in the neural network,
in the neural network,
144
414980
4696
輸入的「像素」、
神經網路裡的「突觸」、
神經網路裡的「突觸」、
07:11
and bird, the output --
145
419700
1585
還有「鳥」這個輸出的字元——
它們是如何運作的。
它們是如何運作的。
07:13
by three variables: x, w and y.
146
421309
3057
它們是由三種變數所組成，
x、w 和 y。
x、w 和 y。
07:16
There are maybe a million or so x's --
147
424853
1811
圖片中可能有一百多萬個 x ——
07:18
a million pixels in that image.
148
426688
1953
100 多萬個像素。
07:20
There are billions or trillions of w's,
149
428665
2446
而 w 可能有數十億或好幾兆個，
07:23
which represent the weights of all
these synapses in the neural network.
these synapses in the neural network.
150
431135
3421
它們代表著神經網路中
各個突觸的權重。
各個突觸的權重。
07:26
And there's a very small number of y's,
151
434580
1875
而這個網路能輸出的 y
07:28
of outputs that that network has.
152
436479
1858
只有少數幾個。
07:30
"Bird" is only four letters, right?
153
438361
1749
「bird」只有四個字母，對吧?
07:33
So let's pretend that this
is just a simple formula,
is just a simple formula,
154
441088
3426
我們假設它的原理是
一個簡單的公式，
一個簡單的公式，
07:36
x "x" w = y.
155
444538
2163
x 「乘以」 w = y
07:38
I'm putting the times in scare quotes
156
446725
2036
我把乘法符號用引號標示起來
07:40
because what's really
going on there, of course,
going on there, of course,
157
448785
2280
因為它其實是一個
07:43
is a very complicated series
of mathematical operations.
of mathematical operations.
158
451089
3046
非常複雜的數學運算概念。
07:47
That's one equation.
159
455172
1221
這個方程式
07:48
There are three variables.
160
456417
1672
有三個變數，
07:50
And we all know
that if you have one equation,
that if you have one equation,
161
458113
2726
我們都知道，如果你想要
解開這個方程式，
解開這個方程式，
07:52
you can solve one variable
by knowing the other two things.
by knowing the other two things.
162
460863
3642
可以從兩個已知數
交叉算出未知的數。
交叉算出未知的數。
07:57
So the problem of inference,
163
465158
3380
所以要推斷出
08:00
that is, figuring out
that the picture of a bird is a bird,
that the picture of a bird is a bird,
164
468562
2873
圖片中的影像是一隻鳥，
08:03
is this one:
165
471459
1274
可以用這種方式得知：
08:04
it's where y is the unknown
and w and x are known.
and w and x are known.
166
472757
3459
y 是未知數，而 w 和 x 是已知數。
08:08
You know the neural network,
you know the pixels.
you know the pixels.
167
476240
2459
已知神經網路和圖片像素，
08:10
As you can see, that's actually
a relatively straightforward problem.
a relatively straightforward problem.
168
478723
3327
其實可以很直接的就得到答案，
08:14
You multiply two times three
and you're done.
and you're done.
169
482074
2186
2x3=6，就做完了。
08:16
I'll show you an artificial neural network
170
484862
2123
我向各位展示一個
08:19
that we've built recently,
doing exactly that.
doing exactly that.
171
487009
2296
我們最近做的人工神經網路，
08:21
This is running in real time
on a mobile phone,
on a mobile phone,
172
489634
2860
它可以在手機上做及時的操作，
08:24
and that's, of course,
amazing in its own right,
amazing in its own right,
173
492518
3313
當然，手機的運算能力相當驚人，
08:27
that mobile phones can do so many
billions and trillions of operations
billions and trillions of operations
174
495855
3468
手機每秒
可以做出數十億至上兆次的運算。
08:31
per second.
175
499347
1248
08:32
What you're looking at is a phone
176
500619
1615
你現在看到的是一隻手機
08:34
looking at one after another
picture of a bird,
picture of a bird,
177
502258
3547
正對著一張張的鳥圖拍照，
08:37
and actually not only saying,
"Yes, it's a bird,"
"Yes, it's a bird,"
178
505829
2715
手機不但可以正確的說出，
「是的，這是一隻鳥。」
「是的，這是一隻鳥。」
08:40
but identifying the species of bird
with a network of this sort.
with a network of this sort.
179
508568
3411
還能透過神經網路分類
分辨出這是哪一種鳥。
分辨出這是哪一種鳥。
08:44
So in that picture,
180
512890
1826
所以，在這些圖片上，
08:46
the x and the w are known,
and the y is the unknown.
and the y is the unknown.
181
514740
3802
x 和 w 是已知，而 y 是未知。
08:50
I'm glossing over the very
difficult part, of course,
difficult part, of course,
182
518566
2508
我現在來解釋一下這個
最困難的 「w」，
最困難的 「w」，
08:53
which is how on earth
do we figure out the w,
do we figure out the w,
183
521098
3861
我們到底是如何算出來的？
08:56
the brain that can do such a thing?
184
524983
2187
為什麼大腦可以做出這樣的判斷？
08:59
How would we ever learn such a model?
185
527194
1834
我們到底是如何學到
這樣的認知模式的？
這樣的認知模式的？
09:01
So this process of learning,
of solving for w,
of solving for w,
186
529418
3233
這個學習的過程，
是一個求解 w 的過程，
是一個求解 w 的過程，
09:04
if we were doing this
with the simple equation
with the simple equation
187
532675
2647
如果我們要解這個一次方程式，
09:07
in which we think about these as numbers,
188
535346
2000
當它們都是數字時，
09:09
we know exactly how to do that: 6 = 2 x w,
189
537370
2687
我們都知道如何解 6=2 x w，
09:12
well, we divide by two and we're done.
190
540081
3312
我們只要把 6 除以 2
就可以得到答案。
就可以得到答案。
09:16
The problem is with this operator.
191
544001
2220
問題在於這個運算符號，
09:18
So, division --
192
546823
1151
除法這個符號——
09:19
we've used division because
it's the inverse to multiplication,
it's the inverse to multiplication,
193
547998
3121
我們會用除法的方式求解，
是因為它跟乘法相反，
是因為它跟乘法相反，
09:23
but as I've just said,
194
551143
1440
但就如同我剛剛提到的，
09:24
the multiplication is a bit of a lie here.
195
552607
2449
乘法在這裡有點像是個幌子。
09:27
This is a very, very complicated,
very non-linear operation;
very non-linear operation;
196
555080
3326
這是非常非常複雜的概念，
它們是「非線性運算」的概念；
它們是「非線性運算」的概念；
09:30
it has no inverse.
197
558430
1704
無法直接用除的求解。
09:32
So we have to figure out a way
to solve the equation
to solve the equation
198
560158
3150
所以，我們要另外
找個方法來解方程式，
找個方法來解方程式，
09:35
without a division operator.
199
563332
2024
而不能直接用除的。
09:37
And the way to do that
is fairly straightforward.
is fairly straightforward.
200
565380
2343
方法相當簡單，
09:39
You just say, let's play
a little algebra trick,
a little algebra trick,
201
567747
2671
可以說，我們只用了點
代數的小技巧，
代數的小技巧，
09:42
and move the six over
to the right-hand side of the equation.
to the right-hand side of the equation.
202
570442
2906
將 6 移動到等號的右邊。
09:45
Now, we're still using multiplication.
203
573372
1826
如此我們就可以繼續用乘法來運算。
09:47
And that zero -- let's think
about it as an error.
about it as an error.
204
575675
3580
而等號左邊的零——
我們把它想像成是誤差。
我們把它想像成是誤差。
09:51
In other words, if we've solved
for w the right way,
for w the right way,
205
579279
2515
換言之，如果要解出 w，
09:53
then the error will be zero.
206
581818
1656
誤差就要變成 0。
09:55
And if we haven't gotten it quite right,
207
583498
1938
如果我們沒找到答案
09:57
the error will be greater than zero.
208
585460
1749
誤差會永遠大於 0。
09:59
So now we can just take guesses
to minimize the error,
to minimize the error,
209
587233
3366
所以，我們現在
只能用猜的來縮小誤差，
只能用猜的來縮小誤差，
10:02
and that's the sort of thing
computers are very good at.
computers are very good at.
210
590623
2687
而這就是電腦非常擅長的地方。
10:05
So you've taken an initial guess:
211
593334
1593
所以，你會從頭開始猜：
10:06
what if w = 0?
212
594951
1156
假設 w=0
10:08
Well, then the error is 6.
213
596131
1240
那誤差會等於6
10:09
What if w = 1? The error is 4.
214
597395
1446
但假如 w=1 呢？誤差等於 4。
10:10
And then the computer can
sort of play Marco Polo,
sort of play Marco Polo,
215
598865
2367
接下來電腦有點像是在玩
馬可波羅探索遊戲，
馬可波羅探索遊戲，
10:13
and drive down the error close to zero.
216
601256
2367
探索到誤差接近零為止。
10:15
As it does that, it's getting
successive approximations to w.
successive approximations to w.
217
603647
3374
當它一直探索到零，
那麼 w 就解出來了。
那麼 w 就解出來了。
10:19
Typically, it never quite gets there,
but after about a dozen steps,
but after about a dozen steps,
218
607045
3656
原則上，它會不停探索直到接近零，
但大約經過多次步驟後，
但大約經過多次步驟後，
10:22
we're up to w = 2.999,
which is close enough.
which is close enough.
219
610725
4624
我們就能得出 w=2.999，
相當接近了。
相當接近了。
10:28
And this is the learning process.
220
616302
1814
這就是電腦學習的過程。
10:30
So remember that what's been going on here
221
618140
2730
回想一下剛剛發生了什麼事情，
10:32
is that we've been taking
a lot of known x's and known y's
a lot of known x's and known y's
222
620894
4378
我們有很多已知的 x 和 y，
10:37
and solving for the w in the middle
through an iterative process.
through an iterative process.
223
625296
3454
透過重複迭代的過程解出了 w。
10:40
It's exactly the same way
that we do our own learning.
that we do our own learning.
224
628774
3556
而這就是我們人類學習的過程，
10:44
We have many, many images as babies
225
632354
2230
我們從小看了很多圖片
10:46
and we get told, "This is a bird;
this is not a bird."
this is not a bird."
226
634608
2633
被告知「這是鳥」，「這不是鳥」；
10:49
And over time, through iteration,
227
637714
2098
經過了一段時間，不停地重複，
10:51
we solve for w, we solve
for those neural connections.
for those neural connections.
228
639836
2928
我們解出了 w，
產生了神經元的連結關係。
產生了神經元的連結關係。
10:55
So now, we've held
x and w fixed to solve for y;
x and w fixed to solve for y;
229
643460
4086
所以現在，我們的 x 和 w
是固定數，可以解出 y；
是固定數，可以解出 y；
10:59
that's everyday, fast perception.
230
647570
1847
這就是我們人類每天
經常性的快速直覺判斷。
經常性的快速直覺判斷。
11:01
We figure out how we can solve for w,
231
649441
1763
我們搞懂了如何解出 w，
11:03
that's learning, which is a lot harder,
232
651228
1903
而學習本身是一條相當艱辛的路程，
11:05
because we need to do error minimization,
233
653155
1985
因為為了讓誤差最小化，
11:07
using a lot of training examples.
234
655164
1687
我們必須使用很多的訓練樣本。
11:08
And about a year ago,
Alex Mordvintsev, on our team,
Alex Mordvintsev, on our team,
235
656875
3187
約一年前，我們團隊的
艾力克斯摩文斯夫
艾力克斯摩文斯夫
11:12
decided to experiment
with what happens if we try solving for x,
with what happens if we try solving for x,
236
660086
3550
決定做個實驗，
看看如果我們試著給出了 w 和 y，
解出來的 x 會變什麼樣。
解出來的 x 會變什麼樣。
11:15
given a known w and a known y.
237
663660
2037
11:18
In other words,
238
666124
1151
換句話說，
11:19
you know that it's a bird,
239
667299
1352
電腦知道它是一隻鳥，
11:20
and you already have your neural network
that you've trained on birds,
that you've trained on birds,
240
668675
3303
電腦有你給它訓練出來
辨識鳥圖片的神經網路，
辨識鳥圖片的神經網路，
11:24
but what is the picture of a bird?
241
672002
2344
但對電腦而言，鳥是怎樣的圖像？
11:27
It turns out that by using exactly
the same error-minimization procedure,
the same error-minimization procedure,
242
675034
5024
原來，使用一模一樣的
「誤差最小化」程序
「誤差最小化」程序
11:32
one can do that with the network
trained to recognize birds,
trained to recognize birds,
243
680082
3430
以及訓練出來
用來辨識鳥的神經網路，
用來辨識鳥的神經網路，
11:35
and the result turns out to be ...
244
683536
3388
你就能辨識出……
11:42
a picture of birds.
245
690400
1305
這是一張鳥圖，
11:44
So this is a picture of birds
generated entirely by a neural network
generated entirely by a neural network
246
692814
3737
所以，這是一張完全由
訓練辨認鳥的神經網路
自行創造出來的鳥圖，
自行創造出來的鳥圖，
11:48
that was trained to recognize birds,
247
696575
1826
11:50
just by solving for x
rather than solving for y,
rather than solving for y,
248
698425
3538
只要透過不斷地重複解出 x，
而不是解 y 就可以了。
11:53
and doing that iteratively.
249
701987
1288
11:55
Here's another fun example.
250
703732
1847
這裡有另一個有趣的範例。
11:57
This was a work made
by Mike Tyka in our group,
by Mike Tyka in our group,
251
705603
3437
我們團隊裡的
另外一位組員麥克泰卡，
另外一位組員麥克泰卡，
12:01
which he calls "Animal Parade."
252
709064
2308
他稱這些畫為《動物大遊行》。
12:03
It reminds me a little bit
of William Kentridge's artworks,
of William Kentridge's artworks,
253
711396
2876
這讓我有點回想起了
威廉肯特基的作品，
威廉肯特基的作品，
12:06
in which he makes sketches, rubs them out,
254
714296
2489
他畫好素描後，擦掉它，
12:08
makes sketches, rubs them out,
255
716809
1460
然後反覆地畫、反覆地擦
12:10
and creates a movie this way.
256
718293
1398
透過這樣的方式，
創造出了一部影片。
創造出了一部影片。
12:11
In this case,
257
719715
1151
在這個展示裡，
12:12
what Mike is doing is varying y
over the space of different animals,
over the space of different animals,
258
720890
3277
麥可做的就是把不同動物的 y ，
12:16
in a network designed
to recognize and distinguish
to recognize and distinguish
259
724191
2382
透過設計好的神經網路，
12:18
different animals from each other.
260
726597
1810
彼此辨認並分別出不一樣的動物。
12:20
And you get this strange, Escher-like
morph from one animal to another.
morph from one animal to another.
261
728431
3751
如此，你就能得到一張像艾雪一樣的
不同動物的變體圖像。
不同動物的變體圖像。
12:26
Here he and Alex together
have tried reducing
have tried reducing
262
734221
4614
這一張是他和艾力克斯一起完成的，
12:30
the y's to a space of only two dimensions,
263
738859
2759
他們試著減少 y 的數量，
將這些圖案丟到一個 2D 平面上，
將這些圖案丟到一個 2D 平面上，
12:33
thereby making a map
out of the space of all things
out of the space of all things
264
741642
3438
透過這個網路的辨識，
12:37
recognized by this network.
265
745104
1719
創造出了這一張有各種動物的地圖。
12:38
Doing this kind of synthesis
266
746847
2023
要做出這樣的綜合體，
12:40
or generation of imagery
over that entire surface,
over that entire surface,
267
748894
2382
或透過整張圖面產出圖像，
12:43
varying y over the surface,
you make a kind of map --
you make a kind of map --
268
751300
2846
你只要在圖面上給出各式各樣的 y ，
你就能做出一張地圖來——
你就能做出一張地圖來——
12:46
a visual map of all the things
the network knows how to recognize.
the network knows how to recognize.
269
754170
3141
一張由神經網路辨識出的視覺地圖。
12:49
The animals are all here;
"armadillo" is right in that spot.
"armadillo" is right in that spot.
270
757335
2865
所有動物都會在這上面，
犰狳就在圖上這個點。
犰狳就在圖上這個點。
12:52
You can do this with other kinds
of networks as well.
of networks as well.
271
760919
2479
你也可以透過不同的神經網路，
做出類似這樣的作品，
做出類似這樣的作品，
12:55
This is a network designed
to recognize faces,
to recognize faces,
272
763422
2874
這一張由辨識臉的神經網路
12:58
to distinguish one face from another.
273
766320
2000
所做出來的作品，
13:00
And here, we're putting
in a y that says, "me,"
in a y that says, "me,"
274
768344
3249
這一張是用「我」當作 y ，
所做出來的圖畫，
所做出來的圖畫，
13:03
my own face parameters.
275
771617
1575
用我的臉當參數。
13:05
And when this thing solves for x,
276
773216
1706
當電腦解出 x 後，
13:06
it generates this rather crazy,
277
774946
2618
它就畫出了這一張相當瘋狂、
13:09
kind of cubist, surreal,
psychedelic picture of me
psychedelic picture of me
278
777588
4428
有點像立體派藝術、
超現實、迷幻效果的我，
超現實、迷幻效果的我，
13:14
from multiple points of view at once.
279
782040
1806
同一張圖卻有不同的視角。
13:15
The reason it looks like
multiple points of view at once
multiple points of view at once
280
783870
2734
而會有這種「同一張圖
不同視角」的感覺，
不同視角」的感覺，
13:18
is because that network is designed
to get rid of the ambiguity
to get rid of the ambiguity
281
786628
3687
是因為這個神經網路的設計，
13:22
of a face being in one pose
or another pose,
or another pose,
282
790339
2476
可以將不同姿勢臉之間的
模糊地帶移除掉，
模糊地帶移除掉，
13:24
being looked at with one kind of lighting,
another kind of lighting.
another kind of lighting.
283
792839
3376
透過觀察不同的光源就可以做到。
13:28
So when you do
this sort of reconstruction,
this sort of reconstruction,
284
796239
2085
所以，當你重新製作圖像時，
13:30
if you don't use some sort of guide image
285
798348
2304
如果你沒有使用指導圖，
13:32
or guide statistics,
286
800676
1211
或特定的統計資料，
13:33
then you'll get a sort of confusion
of different points of view,
of different points of view,
287
801911
3765
那你就能得到來自
不同角度的混合體圖像，
不同角度的混合體圖像，
13:37
because it's ambiguous.
288
805700
1368
因為它是模糊的。
13:39
This is what happens if Alex uses
his own face as a guide image
his own face as a guide image
289
807786
4223
所以如果艾力克斯
用他自己的臉當作指導圖
用他自己的臉當作指導圖
13:44
during that optimization process
to reconstruct my own face.
to reconstruct my own face.
290
812033
3321
在優化過程中重新建造我的臉，
就會產生這樣的圖像。
就會產生這樣的圖像。
13:48
So you can see it's not perfect.
291
816284
2328
各位可以看到，
這作品還不是很完美，
這作品還不是很完美，
13:50
There's still quite a lot of work to do
292
818636
1874
在圖像優化的過程方面，
13:52
on how we optimize
that optimization process.
that optimization process.
293
820534
2453
還有很多工作要做。
13:55
But you start to get something
more like a coherent face,
more like a coherent face,
294
823011
2827
但如果用我的臉當指導圖，
13:57
rendered using my own face as a guide.
295
825862
2014
就能漸漸地顯現出比較
條理分明的臉。
條理分明的臉。
14:00
You don't have to start
with a blank canvas
with a blank canvas
296
828892
2501
你不需要從一張空白的畫布
14:03
or with white noise.
297
831417
1156
或用白雜訊畫起。
14:04
When you're solving for x,
298
832597
1304
當你解出 x 後，
14:05
you can begin with an x,
that is itself already some other image.
that is itself already some other image.
299
833925
3889
你就可以從 x 開始畫起，
因為它本身就有一些圖像。
因為它本身就有一些圖像。
14:09
That's what this little demonstration is.
300
837838
2556
這個小小的展示
說明了它的運作原理。
說明了它的運作原理。
14:12
This is a network
that is designed to categorize
that is designed to categorize
301
840418
4122
這個網路是設計用來
分辨各種不同的物體，
分辨各種不同的物體，
14:16
all sorts of different objects --
man-made structures, animals ...
man-made structures, animals ...
302
844564
3119
像是人造結構、動物……等。
14:19
Here we're starting
with just a picture of clouds,
with just a picture of clouds,
303
847707
2593
這一張畫我們是從
雲朵的圖像開始畫起的，
雲朵的圖像開始畫起的，
14:22
and as we optimize,
304
850324
1671
當我們把它優化後，
14:24
basically, this network is figuring out
what it sees in the clouds.
what it sees in the clouds.
305
852019
4486
基本上，這個神經網路
正在搞懂它在雲朵中看見了什麼。
正在搞懂它在雲朵中看見了什麼。
14:28
And the more time
you spend looking at this,
you spend looking at this,
306
856931
2320
當你看得越久，
14:31
the more things you also
will see in the clouds.
will see in the clouds.
307
859275
2753
你就能在雲層中看得越多。
14:35
You could also use the face network
to hallucinate into this,
to hallucinate into this,
308
863004
3375
你也可以運用人臉網路
讓它產生幻覺，
讓它產生幻覺，
14:38
and you get some pretty crazy stuff.
309
866403
1812
然後就會跑出相當瘋狂的畫作。
14:40
(Laughter)
310
868239
1150
（笑聲）
14:42
Or, Mike has done some other experiments
311
870401
2744
或者，麥可已經有作出
一些其它的實驗，
一些其它的實驗，
14:45
in which he takes that cloud image,
312
873169
3905
他用那張雲朵的圖像，
14:49
hallucinates, zooms, hallucinates,
zooms hallucinates, zooms.
zooms hallucinates, zooms.
313
877098
3507
使電腦產生幻覺、然後放大、
產生幻覺、再放大。
產生幻覺、再放大。
14:52
And in this way,
314
880629
1151
用這樣的方式，
14:53
you can get a sort of fugue state
of the network, I suppose,
of the network, I suppose,
315
881804
3675
我在想，你就能得到一種
像是在神遊狀態的網路，
像是在神遊狀態的網路，
14:57
or a sort of free association,
316
885503
3680
或者像是一種無拘束的聯想，
15:01
in which the network
is eating its own tail.
is eating its own tail.
317
889207
2227
彷彿神經網路正在吃著自己的尾巴。
15:03
So every image is now the basis for,
318
891458
3421
所以每一張圖像基本上像是正在想：
15:06
"What do I think I see next?
319
894903
1421
「我接下來會看到什麼？
15:08
What do I think I see next?
What do I think I see next?"
What do I think I see next?"
320
896348
2803
接下來會看到什麼？
接下來會看到什麼？」
接下來會看到什麼？」
15:11
I showed this for the first time in public
321
899487
2936
我第一次在一個
公眾場合上展示這個影片，
公眾場合上展示這個影片，
15:14
to a group at a lecture in Seattle
called "Higher Education" --
called "Higher Education" --
322
902447
5437
是在西雅圖的「高等教育」
機構做演說時展示的，
機構做演說時展示的，
15:19
this was right after
marijuana was legalized.
marijuana was legalized.
323
907908
2437
當時剛好是大麻剛合法化的時候。
15:22
(Laughter)
324
910369
2415
（笑聲）
15:26
So I'd like to finish up quickly
325
914627
2104
所以，我快速總結一下，
15:28
by just noting that this technology
is not constrained.
is not constrained.
326
916755
4255
這項技術並不會受到約束。
15:33
I've shown you purely visual examples
because they're really fun to look at.
because they're really fun to look at.
327
921034
3665
我剛剛展示的是純粹的視覺範例，
因為觀察它的變化，真的很好玩。
因為觀察它的變化，真的很好玩。
15:36
It's not a purely visual technology.
328
924723
2451
它不單只有視覺科技。
15:39
Our artist collaborator, Ross Goodwin,
329
927198
1993
我們的藝術合作者，羅斯谷穎
已經做了一些實驗，
已經做了一些實驗，
15:41
has done experiments involving
a camera that takes a picture,
a camera that takes a picture,
330
929215
3671
他用相機拍了一張照片，
15:44
and then a computer in his backpack
writes a poem using neural networks,
writes a poem using neural networks,
331
932910
4234
然後他背包裡的電腦
會根據圖片上的內容，
會根據圖片上的內容，
15:49
based on the contents of the image.
332
937168
1944
透過神經網路，創作出一首詩。
15:51
And that poetry neural network
has been trained
has been trained
333
939136
2947
這個會作詩的神經網路
15:54
on a large corpus of 20th-century poetry.
334
942107
2234
是透過大量 20 世紀的詩集
所訓練出來的，
所訓練出來的，
15:56
And the poetry is, you know,
335
944365
1499
而做出來的詩，
15:57
I think, kind of not bad, actually.
336
945888
1914
實際上，我覺得還得不錯。
15:59
(Laughter)
337
947826
1384
（笑聲）
16:01
In closing,
338
949234
1159
整體而言，
16:02
I think that per Michelangelo,
339
950417
2132
我在想，米開朗基羅，
16:04
I think he was right;
340
952573
1234
他是對的；
16:05
perception and creativity
are very intimately connected.
are very intimately connected.
341
953831
3436
感知和創意的關係是相當緊密的。
16:09
What we've just seen are neural networks
342
957611
2634
我們剛剛看的神經網路，
16:12
that are entirely trained to discriminate,
343
960269
2303
它們是被訓練出來分辯
16:14
or to recognize different
things in the world,
things in the world,
344
962596
2242
或辨認世界上不同的東西，
16:16
able to be run in reverse, to generate.
345
964862
3161
也可以反過來，自行創作出東西來。
16:20
One of the things that suggests to me
346
968047
1783
而我從中所得到的
16:21
is not only that
Michelangelo really did see
Michelangelo really did see
347
969854
2398
不僅有米開朗基羅的啟發：
16:24
the sculpture in the blocks of stone,
348
972276
2452
「看見石頭裡的雕像」，
16:26
but that any creature,
any being, any alien
any being, any alien
349
974752
3638
還有任何能做出感知活動的
生物、生命、外來物種
生物、生命、外來物種
16:30
that is able to do
perceptual acts of that sort
perceptual acts of that sort
350
978414
3657
都能透過這樣的方式
16:34
is also able to create
351
982095
1375
被呈現並創造出來，
16:35
because it's exactly the same
machinery that's used in both cases.
machinery that's used in both cases.
352
983494
3224
因為這兩者與剛才舉的例子
都有著相同的機制。
都有著相同的機制。
16:38
Also, I think that perception
and creativity are by no means
and creativity are by no means
353
986742
4532
我也認為，感知及創意
不是只有我們人類獨有。
16:43
uniquely human.
354
991298
1210
16:44
We start to have computer models
that can do exactly these sorts of things.
that can do exactly these sorts of things.
355
992532
3708
我們已經有電腦模式
可以做出相當類似的事。
可以做出相當類似的事。
16:48
And that ought to be unsurprising;
the brain is computational.
the brain is computational.
356
996264
3328
所以不需要感到驚訝；
因為大腦是會運算的。
因為大腦是會運算的。
16:51
And finally,
357
999616
1657
最後，我要說的是，
16:53
computing began as an exercise
in designing intelligent machinery.
in designing intelligent machinery.
358
1001297
4668
設計智能機器已經開始成為
電腦界的活動。
電腦界的活動。
16:57
It was very much modeled after the idea
359
1005989
2462
在如何讓機器更智能的領域方面，
17:00
of how could we make machines intelligent.
360
1008475
3013
已經有很多的模式產生。
17:03
And we finally are starting to fulfill now
361
1011512
2162
我們終於開始
17:05
some of the promises
of those early pioneers,
of those early pioneers,
362
1013698
2406
完成一些早期前輩們
17:08
of Turing and von Neumann
363
1016128
1713
像是圖靈、馮諾伊曼、
17:09
and McCulloch and Pitts.
364
1017865
2265
馬庫洛奇和皮斯的期望。
17:12
And I think that computing
is not just about accounting
is not just about accounting
365
1020154
4098
而我也認為電腦不是只有拿來計算
17:16
or playing Candy Crush or something.
366
1024276
2147
或玩玩 Candy Crush 而已，
17:18
From the beginning,
we modeled them after our minds.
we modeled them after our minds.
367
1026447
2578
回到初衷，我們想要的
是讓電腦能仿效人腦。
是讓電腦能仿效人腦。
17:21
And they give us both the ability
to understand our own minds better
to understand our own minds better
368
1029049
3269
它不僅讓我們更了解了人類的心智，
並讓我們獲得延伸發展心智的能力。
17:24
and to extend them.
369
1032342
1529
17:26
Thank you very much.
370
1034627
1167
非常感謝大家。
17:27
(Applause)
371
1035818
5939
（掌聲）
Translated by Yi-Fan Yu
ABOUT THE SPEAKER
Blaise Agüera y Arcas - Software architectBlaise Agüera y Arcas works on machine learning at Google. Previously a Distinguished Engineer at Microsoft, he has worked on augmented reality, mapping, wearable computing and natural user interfaces.
Why you should listen
Blaise Agüera y Arcas is principal scientist at Google, where he leads a team working on machine intelligence for mobile devices. His group works extensively with deep neural nets for machine perception and distributed learning, and it also investigates so-called "connectomics" research, assessing maps of connections within the brain.
Agüera y Arcas' background is as multidimensional as the visions he helps create. In the 1990s, he authored patents on both video compression and 3D visualization techniques, and in 2001, he made an influential computational discovery that cast doubt on Gutenberg's role as the father of movable type.
He also created Seadragon (acquired by Microsoft in 2006), the visualization technology that gives Photosynth its amazingly smooth digital rendering and zoom capabilities. Photosynth itself is a vastly powerful piece of software capable of taking a wide variety of images, analyzing them for similarities, and grafting them together into an interactive three-dimensional space. This seamless patchwork of images can be viewed via multiple angles and magnifications, allowing us to look around corners or “fly” in for a (much) closer look. Simply put, it could utterly transform the way we experience digital images.
He joined Microsoft when Seadragon was acquired by Live Labs in 2006. Shortly after the acquisition of Seadragon, Agüera y Arcas directed his team in a collaboration with Microsoft Research and the University of Washington, leading to the first public previews of Photosynth several months later. His TED Talk on Seadragon and Photosynth in 2007 is rated one of TED's "most jaw-dropping." He returned to TED in 2010 to demo Bing’s augmented reality maps.
Fun fact: According to the author, Agüera y Arcas is the inspiration for the character Elgin in the 2012 best-selling novel Where'd You Go, Bernadette?
Blaise Agüera y Arcas | Speaker | TED.com