1
00:00:00,556 --> 00:00:04,573
Our emotions influence
every aspect of our lives,

2
00:00:04,573 --> 00:00:08,149
from our health and how we learn,
to how we do business and make decisions,

3
00:00:08,149 --> 00:00:09,922
big ones and small.

4
00:00:10,672 --> 00:00:14,162
Our emotions also influence
how we connect with one another.

5
00:00:15,132 --> 00:00:19,108
We've evolved to live
in a world like this,

6
00:00:19,108 --> 00:00:23,427
but instead, we're living
more and more of our lives like this --

7
00:00:23,427 --> 00:00:26,561
this is the text message
from my daughter last night --

8
00:00:26,561 --> 00:00:29,301
in a world that's devoid of emotion.

9
00:00:29,301 --> 00:00:31,252
So I'm on a mission to change that.

10
00:00:31,252 --> 00:00:35,343
I want to bring emotions
back into our digital experiences.

11
00:00:36,223 --> 00:00:39,300
I started on this path 15 years ago.

12
00:00:39,300 --> 00:00:41,366
I was a computer scientist in Egypt,

13
00:00:41,366 --> 00:00:45,871
and I had just gotten accepted to
a Ph.D. program at Cambridge University.

14
00:00:45,871 --> 00:00:47,984
So I did something quite unusual

15
00:00:47,984 --> 00:00:52,209
for a young newlywed Muslim Egyptian wife:

16
00:00:53,599 --> 00:00:56,598
With the support of my husband,
who had to stay in Egypt,

17
00:00:56,598 --> 00:00:59,616
I packed my bags and I moved to England.

18
00:00:59,616 --> 00:01:02,844
At Cambridge, thousands of miles
away from home,

19
00:01:02,844 --> 00:01:06,257
I realized I was spending
more hours with my laptop

20
00:01:06,257 --> 00:01:08,486
than I did with any other human.

21
00:01:08,486 --> 00:01:13,339
Yet despite this intimacy, my laptop
had absolutely no idea how I was feeling.

22
00:01:13,339 --> 00:01:16,550
It had no idea if I was happy,

23
00:01:16,550 --> 00:01:19,538
having a bad day, or stressed, confused,

24
00:01:19,538 --> 00:01:22,460
and so that got frustrating.

25
00:01:23,600 --> 00:01:28,831
Even worse, as I communicated
online with my family back home,

26
00:01:29,421 --> 00:01:32,703
I felt that all my emotions
disappeared in cyberspace.

27
00:01:32,703 --> 00:01:37,858
I was homesick, I was lonely,
and on some days I was actually crying,

28
00:01:37,858 --> 00:01:42,786
but all I had to communicate
these emotions was this.

29
00:01:42,786 --> 00:01:44,806
(Laughter)

30
00:01:44,806 --> 00:01:49,780
Today's technology
has lots of I.Q., but no E.Q.;

31
00:01:49,780 --> 00:01:52,956
lots of cognitive intelligence,
but no emotional intelligence.

32
00:01:52,956 --> 00:01:55,153
So that got me thinking,

33
00:01:55,153 --> 00:01:58,777
what if our technology
could sense our emotions?

34
00:01:58,777 --> 00:02:02,853
What if our devices could sense
how we felt and reacted accordingly,

35
00:02:02,853 --> 00:02:05,866
just the way an emotionally
intelligent friend would?

36
00:02:06,666 --> 00:02:10,230
Those questions led me and my team

37
00:02:10,230 --> 00:02:14,607
to create technologies that can read
and respond to our emotions,

38
00:02:14,607 --> 00:02:17,697
and our starting point was the human face.

39
00:02:18,577 --> 00:02:21,750
So our human face happens to be
one of the most powerful channels

40
00:02:21,750 --> 00:02:25,766
that we all use to communicate
social and emotional states,

41
00:02:25,766 --> 00:02:28,776
everything from enjoyment, surprise,

42
00:02:28,776 --> 00:02:32,979
empathy and curiosity.

43
00:02:32,979 --> 00:02:37,907
In emotion science, we call each
facial muscle movement an action unit.

44
00:02:37,907 --> 00:02:40,832
So for example, action unit 12,

45
00:02:40,832 --> 00:02:42,870
it's not a Hollywood blockbuster,

46
00:02:42,870 --> 00:02:46,312
it is actually a lip corner pull,
which is the main component of a smile.

47
00:02:46,312 --> 00:02:49,300
Try it everybody. Let's get
some smiles going on.

48
00:02:49,300 --> 00:02:51,954
Another example is action unit 4.
It's the brow furrow.

49
00:02:51,954 --> 00:02:54,192
It's when you draw your eyebrows together

50
00:02:54,192 --> 00:02:56,459
and you create all
these textures and wrinkles.

51
00:02:56,459 --> 00:03:00,754
We don't like them, but it's
a strong indicator of a negative emotion.

52
00:03:00,754 --> 00:03:02,960
So we have about 45 of these action units,

53
00:03:02,960 --> 00:03:06,350
and they combine to express
hundreds of emotions.

54
00:03:06,350 --> 00:03:10,251
Teaching a computer to read
these facial emotions is hard,

55
00:03:10,251 --> 00:03:13,223
because these action units,
they can be fast, they're subtle,

56
00:03:13,223 --> 00:03:15,777
and they combine in many different ways.

57
00:03:15,777 --> 00:03:19,515
So take, for example,
the smile and the smirk.

58
00:03:19,515 --> 00:03:23,268
They look somewhat similar,
but they mean very different things.

59
00:03:23,268 --> 00:03:24,986
(Laughter)

60
00:03:24,986 --> 00:03:27,990
So the smile is positive,

61
00:03:27,990 --> 00:03:29,260
a smirk is often negative.

62
00:03:29,260 --> 00:03:33,136
Sometimes a smirk
can make you become famous.

63
00:03:33,136 --> 00:03:35,960
But seriously, it's important
for a computer to be able

64
00:03:35,960 --> 00:03:38,815
to tell the difference
between the two expressions.

65
00:03:38,815 --> 00:03:40,627
So how do we do that?

66
00:03:40,627 --> 00:03:42,414
We give our algorithms

67
00:03:42,414 --> 00:03:46,524
tens of thousands of examples
of people we know to be smiling,

68
00:03:46,524 --> 00:03:49,589
from different ethnicities, ages, genders,

69
00:03:49,589 --> 00:03:52,400
and we do the same for smirks.

70
00:03:52,400 --> 00:03:53,954
And then, using deep learning,

71
00:03:53,954 --> 00:03:56,810
the algorithm looks for all these
textures and wrinkles

72
00:03:56,810 --> 00:03:59,390
and shape changes on our face,

73
00:03:59,390 --> 00:04:02,592
and basically learns that all smiles
have common characteristics,

74
00:04:02,592 --> 00:04:05,773
all smirks have subtly
different characteristics.

75
00:04:05,773 --> 00:04:08,141
And the next time it sees a new face,

76
00:04:08,141 --> 00:04:10,440
it essentially learns that

77
00:04:10,440 --> 00:04:13,473
this face has the same
characteristics of a smile,

78
00:04:13,473 --> 00:04:17,751
and it says, "Aha, I recognize this.
This is a smile expression."

79
00:04:18,381 --> 00:04:21,181
So the best way to demonstrate
how this technology works

80
00:04:21,181 --> 00:04:23,317
is to try a live demo,

81
00:04:23,317 --> 00:04:27,230
so I need a volunteer,
preferably somebody with a face.

82
00:04:27,230 --> 00:04:29,564
(Laughter)

83
00:04:29,564 --> 00:04:32,335
Cloe's going to be our volunteer today.

84
00:04:33,325 --> 00:04:37,783
So over the past five years, we've moved
from being a research project at MIT

85
00:04:37,783 --> 00:04:38,939
to a company,

86
00:04:38,939 --> 00:04:42,131
where my team has worked really hard
to make this technology work,

87
00:04:42,131 --> 00:04:44,540
as we like to say, in the wild.

88
00:04:44,540 --> 00:04:47,210
And we've also shrunk it so that
the core emotion engine

89
00:04:47,210 --> 00:04:50,530
works on any mobile device
with a camera, like this iPad.

90
00:04:50,530 --> 00:04:53,316
So let's give this a try.

91
00:04:54,756 --> 00:04:58,680
As you can see, the algorithm
has essentially found Cloe's face,

92
00:04:58,680 --> 00:05:00,372
so it's this white bounding box,

93
00:05:00,372 --> 00:05:02,943
and it's tracking the main
feature points on her face,

94
00:05:02,943 --> 00:05:05,799
so her eyebrows, her eyes,
her mouth and her nose.

95
00:05:05,799 --> 00:05:08,786
The question is,
can it recognize her expression?

96
00:05:08,786 --> 00:05:10,457
So we're going to test the machine.

97
00:05:10,457 --> 00:05:14,643
So first of all, give me your poker face.
Yep, awesome. (Laughter)

98
00:05:14,643 --> 00:05:17,456
And then as she smiles,
this is a genuine smile, it's great.

99
00:05:17,456 --> 00:05:19,756
So you can see the green bar
go up as she smiles.

100
00:05:19,756 --> 00:05:20,978
Now that was a big smile.

101
00:05:20,978 --> 00:05:24,021
Can you try a subtle smile
to see if the computer can recognize?

102
00:05:24,021 --> 00:05:26,352
It does recognize subtle smiles as well.

103
00:05:26,352 --> 00:05:28,477
We've worked really hard
to make that happen.

104
00:05:28,477 --> 00:05:31,439
And then eyebrow raised,
indicator of surprise.

105
00:05:31,439 --> 00:05:35,688
Brow furrow, which is
an indicator of confusion.

106
00:05:35,688 --> 00:05:39,695
Frown. Yes, perfect.

107
00:05:39,695 --> 00:05:43,188
So these are all the different
action units. There's many more of them.

108
00:05:43,188 --> 00:05:45,220
This is just a slimmed-down demo.

109
00:05:45,220 --> 00:05:48,368
But we call each reading
an emotion data point,

110
00:05:48,368 --> 00:05:51,337
and then they can fire together
to portray different emotions.

111
00:05:51,337 --> 00:05:55,990
So on the right side of the demo --
look like you're happy.

112
00:05:55,990 --> 00:05:57,444
So that's joy. Joy fires up.

113
00:05:57,444 --> 00:05:59,371
And then give me a disgust face.

114
00:05:59,371 --> 00:06:03,643
Try to remember what it was like
when Zayn left One Direction.

115
00:06:03,643 --> 00:06:05,153
(Laughter)

116
00:06:05,153 --> 00:06:09,495
Yeah, wrinkle your nose. Awesome.

117
00:06:09,495 --> 00:06:13,226
And the valence is actually quite
negative, so you must have been a big fan.

118
00:06:13,226 --> 00:06:15,926
So valence is how positive
or negative an experience is,

119
00:06:15,926 --> 00:06:18,712
and engagement is how
expressive she is as well.

120
00:06:18,712 --> 00:06:22,126
So imagine if Cloe had access
to this real-time emotion stream,

121
00:06:22,126 --> 00:06:24,935
and she could share it
with anybody she wanted to.

122
00:06:24,935 --> 00:06:27,858
Thank you.

123
00:06:27,858 --> 00:06:32,479
(Applause)

124
00:06:33,749 --> 00:06:39,019
So, so far, we have amassed
12 billion of these emotion data points.

125
00:06:39,019 --> 00:06:41,630
It's the largest emotion
database in the world.

126
00:06:41,630 --> 00:06:44,593
We've collected it
from 2.9 million face videos,

127
00:06:44,593 --> 00:06:47,193
people who have agreed
to share their emotions with us,

128
00:06:47,193 --> 00:06:50,398
and from 75 countries around the world.

129
00:06:50,398 --> 00:06:52,113
It's growing every day.

130
00:06:52,603 --> 00:06:54,670
It blows my mind away

131
00:06:54,670 --> 00:06:57,865
that we can now quantify something
as personal as our emotions,

132
00:06:57,865 --> 00:07:00,100
and we can do it at this scale.

133
00:07:00,100 --> 00:07:02,277
So what have we learned to date?

134
00:07:03,057 --> 00:07:05,388
Gender.

135
00:07:05,388 --> 00:07:09,034
Our data confirms something
that you might suspect.

136
00:07:09,034 --> 00:07:10,891
Women are more expressive than men.

137
00:07:10,891 --> 00:07:13,574
Not only do they smile more,
their smiles last longer,

138
00:07:13,574 --> 00:07:16,478
and we can now really quantify
what it is that men and women

139
00:07:16,478 --> 00:07:18,614
respond to differently.

140
00:07:18,614 --> 00:07:20,904
Let's do culture: So in the United States,

141
00:07:20,904 --> 00:07:24,108
women are 40 percent
more expressive than men,

142
00:07:24,108 --> 00:07:27,753
but curiously, we don't see any difference
in the U.K. between men and women.

143
00:07:27,753 --> 00:07:30,259
(Laughter)

144
00:07:31,296 --> 00:07:35,323
Age: People who are 50 years and older

145
00:07:35,323 --> 00:07:38,759
are 25 percent more emotive
than younger people.

146
00:07:39,899 --> 00:07:43,751
Women in their 20s smile a lot more
than men the same age,

147
00:07:43,751 --> 00:07:47,590
perhaps a necessity for dating.

148
00:07:47,590 --> 00:07:50,207
But perhaps what surprised us
the most about this data

149
00:07:50,207 --> 00:07:53,410
is that we happen
to be expressive all the time,

150
00:07:53,410 --> 00:07:56,243
even when we are sitting
in front of our devices alone,

151
00:07:56,243 --> 00:07:59,517
and it's not just when we're watching
cat videos on Facebook.

152
00:08:00,217 --> 00:08:03,227
We are expressive when we're emailing,
texting, shopping online,

153
00:08:03,227 --> 00:08:05,527
or even doing our taxes.

154
00:08:05,527 --> 00:08:07,919
Where is this data used today?

155
00:08:07,919 --> 00:08:10,682
In understanding how we engage with media,

156
00:08:10,682 --> 00:08:13,166
so understanding virality
and voting behavior;

157
00:08:13,166 --> 00:08:15,906
and also empowering
or emotion-enabling technology,

158
00:08:15,906 --> 00:08:20,527
and I want to share some examples
that are especially close to my heart.

159
00:08:21,197 --> 00:08:24,265
Emotion-enabled wearable glasses
can help individuals

160
00:08:24,265 --> 00:08:27,493
who are visually impaired
read the faces of others,

161
00:08:27,493 --> 00:08:31,680
and it can help individuals
on the autism spectrum interpret emotion,

162
00:08:31,680 --> 00:08:34,458
something that they really struggle with.

163
00:08:35,918 --> 00:08:38,777
In education, imagine
if your learning apps

164
00:08:38,777 --> 00:08:41,587
sense that you're confused and slow down,

165
00:08:41,587 --> 00:08:43,444
or that you're bored, so it's sped up,

166
00:08:43,444 --> 00:08:46,413
just like a great teacher
would in a classroom.

167
00:08:47,043 --> 00:08:49,644
What if your wristwatch tracked your mood,

168
00:08:49,644 --> 00:08:52,337
or your car sensed that you're tired,

169
00:08:52,337 --> 00:08:54,885
or perhaps your fridge
knows that you're stressed,

170
00:08:54,885 --> 00:09:00,951
so it auto-locks to prevent you
from binge eating. (Laughter)

171
00:09:00,951 --> 00:09:03,668
I would like that, yeah.

172
00:09:03,668 --> 00:09:05,595
What if, when I was in Cambridge,

173
00:09:05,595 --> 00:09:07,908
I had access to my real-time
emotion stream,

174
00:09:07,908 --> 00:09:11,437
and I could share that with my family
back home in a very natural way,

175
00:09:11,437 --> 00:09:15,408
just like I would've if we were all
in the same room together?

176
00:09:15,408 --> 00:09:18,550
I think five years down the line,

177
00:09:18,550 --> 00:09:20,887
all our devices are going
to have an emotion chip,

178
00:09:20,887 --> 00:09:24,951
and we won't remember what it was like
when we couldn't just frown at our device

179
00:09:24,951 --> 00:09:29,200
and our device would say, "Hmm,
you didn't like that, did you?"

180
00:09:29,200 --> 00:09:32,961
Our biggest challenge is that there are
so many applications of this technology,

181
00:09:32,961 --> 00:09:35,864
my team and I realize that we can't
build them all ourselves,

182
00:09:35,864 --> 00:09:39,360
so we've made this technology available
so that other developers

183
00:09:39,360 --> 00:09:41,474
can get building and get creative.

184
00:09:41,474 --> 00:09:45,560
We recognize that
there are potential risks

185
00:09:45,560 --> 00:09:47,627
and potential for abuse,

186
00:09:47,627 --> 00:09:50,576
but personally, having spent
many years doing this,

187
00:09:50,576 --> 00:09:53,548
I believe that the benefits to humanity

188
00:09:53,548 --> 00:09:55,823
from having emotionally
intelligent technology

189
00:09:55,823 --> 00:09:59,399
far outweigh the potential for misuse.

190
00:09:59,399 --> 00:10:01,930
And I invite you all to be
part of the conversation.

191
00:10:01,930 --> 00:10:04,484
The more people who know
about this technology,

192
00:10:04,484 --> 00:10:07,661
the more we can all have a voice
in how it's being used.

193
00:10:09,081 --> 00:10:13,655
So as more and more
of our lives become digital,

194
00:10:13,655 --> 00:10:17,153
we are fighting a losing battle
trying to curb our usage of devices

195
00:10:17,153 --> 00:10:19,382
in order to reclaim our emotions.

196
00:10:20,622 --> 00:10:24,536
So what I'm trying to do instead
is to bring emotions into our technology

197
00:10:24,536 --> 00:10:26,765
and make our technologies more responsive.

198
00:10:26,765 --> 00:10:29,435
So I want those devices
that have separated us

199
00:10:29,435 --> 00:10:31,897
to bring us back together.

200
00:10:31,897 --> 00:10:36,485
And by humanizing technology,
we have this golden opportunity

201
00:10:36,485 --> 00:10:39,782
to reimagine how we
connect with machines,

202
00:10:39,782 --> 00:10:44,263
and therefore, how we, as human beings,

203
00:10:44,263 --> 00:10:46,167
connect with one another.

204
00:10:46,167 --> 00:10:48,327
Thank you.

205
00:10:48,327 --> 00:10:51,640
(Applause)