A headset that reads your brainwaves | Tan Le

377,362 views ใƒป 2010-07-22

TED


ืื ื ืœื—ืฅ ืคืขืžื™ื™ื ืขืœ ื”ื›ืชื•ื‘ื™ื•ืช ื‘ืื ื’ืœื™ืช ืœืžื˜ื” ื›ื“ื™ ืœื”ืคืขื™ืœ ืืช ื”ืกืจื˜ื•ืŸ.

ืžืชืจื’ื: Ron Bentata ืžื‘ืงืจ: Ido Dekkers
00:16
Up until now, our communication with machines
0
16260
2000
ืขื“ ื›ื”, ื”ืชืงืฉื•ืจืช ืฉืœื ื• ืขื ืžื›ื•ื ื•ืช
00:18
has always been limited
1
18260
2000
ื”ื™ื™ืชื” ืชืžื™ื“ ืžื•ื’ื‘ืœืช
00:20
to conscious and direct forms.
2
20260
2000
ืœื“ืจื›ื™ื ื™ืฉื™ืจื•ืช ื•ืžื•ื“ืขื•ืช.
00:22
Whether it's something simple
3
22260
2000
ื‘ื™ืŸ ืื ื–ื” ืžืฉื”ื• ืคืฉื•ื˜
00:24
like turning on the lights with a switch,
4
24260
2000
ื›ืžื• ืœื”ื“ืœื™ืง ืืช ื”ืื•ืจื•ืช ื‘ืืžืฆืขื•ืช ื”ืžืชื’,
00:26
or even as complex as programming robotics,
5
26260
3000
ื•ื‘ื™ืŸ ืื ืžื“ื•ื‘ืจ ื‘ืชื›ื ื•ืช ืจื•ื‘ื•ื˜ื™ื ืžื•ืจื›ื‘,
00:29
we have always had to give a command to a machine,
6
29260
3000
ืชืžื™ื“ ื”ื™ื™ื ื• ืฆืจื™ื›ื™ื ืœืชืช ืคืงื•ื“ื” ืœืžื›ื•ื ื”,
00:32
or even a series of commands,
7
32260
2000
ืื• ืืคื™ืœื• ืฉื•ืจื” ืฉืœ ืคืงื•ื“ื•ืช,
00:34
in order for it to do something for us.
8
34260
3000
ืขืœ ืžื ืช ืฉื–ื• ืชืขืฉื” ืžืฉื”ื• ืขื‘ื•ืจื™ื ื•.
00:37
Communication between people, on the other hand,
9
37260
2000
ืชืงืฉื•ืจืช ื‘ื™ืŸ ืื ืฉื™ื ืžืฆื“ ืฉื ื™,
00:39
is far more complex and a lot more interesting
10
39260
3000
ื”ื™ื ื” ืžื•ืจื›ื‘ืช ื”ืจื‘ื” ื™ื•ืชืจ ื•ืžืขื ื™ื™ื ืช ืžืื•ื“,
00:42
because we take into account
11
42260
2000
ืžื›ื™ื•ื•ืŸ ืฉืื ื• ืœื•ืงื—ื™ื ื‘ื—ืฉื‘ื•ืŸ
00:44
so much more than what is explicitly expressed.
12
44260
3000
ื”ืจื‘ื” ืžืขื‘ืจ ืœื‘ื™ื˜ื•ื™ ื”ืžืคื•ืจืฉ ืฉืœ ื”ื“ื‘ืจื™ื.
00:47
We observe facial expressions, body language,
13
47260
3000
ืื ื• ืฆื•ืคื™ื ื‘ื”ื‘ืขื•ืช ื”ืคื ื™ื, ืฉืคืช ื”ื’ื•ืฃ,
00:50
and we can intuit feelings and emotions
14
50260
2000
ื•ืื ื• ื™ื›ื•ืœ ืœืคืจืฉ ืชื—ื•ืฉื•ืช ื•ืจื’ืฉื•ืช
00:52
from our dialogue with one another.
15
52260
3000
ืžื”ื“ื™ืืœื•ื’ ืฉืœื ื• ืขื ื”ืื—ืจ.
00:55
This actually forms a large part
16
55260
2000
ื–ื”ื• ืœืžืขืฉื” ืžืจื›ื™ื‘ ืžืฉืžืขื•ืชื™
00:57
of our decision-making process.
17
57260
2000
ืžืชื”ืœื™ืš ืงื‘ืœืช ื”ื”ื—ืœื˜ื•ืช ืฉืœื ื•.
00:59
Our vision is to introduce
18
59260
2000
ื”ื—ื–ื•ืŸ ืฉืœื ื• ื”ื•ื ืœื”ื›ื ื™ืก
01:01
this whole new realm of human interaction
19
61260
3000
ืืช ื”ืขื•ืœื ื”ื—ื“ืฉ ืฉืœ ืื™ื ื˜ืจืืงืฆื™ื” ืื ื•ืฉื™ืช
01:04
into human-computer interaction
20
64260
2000
ืœืื™ื ื˜ืจืืงืฆื™ื” ืฉื‘ื™ืŸ ืื“ื ืœืžื›ื•ื ื”.
01:06
so that computers can understand
21
66260
2000
ื›ืš ืฉืžื—ืฉื‘ื™ื ื™ื•ื›ืœื• ืœื”ื‘ื™ืŸ
01:08
not only what you direct it to do,
22
68260
2000
ืœื ืจืง ืžื” ืฉืื ื• ืื•ืžืจื™ื ืœื”ื ืœืขืฉื•ืช,
01:10
but it can also respond
23
70260
2000
ืืš ื”ื ื’ื ื™ื•ื›ืœื• ืœื”ื’ื™ื‘
01:12
to your facial expressions
24
72260
2000
ืœื”ื‘ืขื•ืช ื”ืคื ื™ื ืฉืœืš
01:14
and emotional experiences.
25
74260
2000
ื•ืœื”ื‘ืขื•ืช ื”ื’ื•ืฃ.
01:16
And what better way to do this
26
76260
2000
ื•ืื™ื–ื• ื“ืจืš ื˜ื•ื‘ื” ื™ื•ืชืจ ืœืขืฉื•ืช ื–ืืช
01:18
than by interpreting the signals
27
78260
2000
ืžืืฉืจ ืœืคืขื ื— ืืช ื”ืื•ืชื•ืช
01:20
naturally produced by our brain,
28
80260
2000
ื”ืžื•ืคืงื™ื ื‘ืื•ืคืŸ ื˜ื‘ืขื™ ืข"ื™ ื”ืžื•ื— ืฉืœื ื•,
01:22
our center for control and experience.
29
82260
3000
ื”ืžืจื›ื– ืฉืœื ื• ืœืฉืœื™ื˜ื” ื•ื—ื•ื•ื™ื”.
01:25
Well, it sounds like a pretty good idea,
30
85260
2000
ื•ื‘ื›ืŸ, ื–ื” ื ืฉืžืข ื›ืžื• ืจืขื™ื•ืŸ ื˜ื•ื‘ ืœืžื“ื™,
01:27
but this task, as Bruno mentioned,
31
87260
2000
ืืš ื”ืžืฉื™ืžื” ื”ื–ื•, ื›ืžื• ืฉื‘ืจื•ื ื• ืฆื™ื™ืŸ,
01:29
isn't an easy one for two main reasons:
32
89260
3000
ืœื ืงืœื” ื‘ืฉืœ ืฉืชื™ ืกื™ื‘ื•ืช:
01:32
First, the detection algorithms.
33
92260
3000
ื”ืจืืฉื•ื ื”, ืืœื’ื•ืจื™ืชื ื”ื–ื™ื”ื•ื™.
01:35
Our brain is made up of
34
95260
2000
ื”ืžื•ื— ืฉืœื ื• ืžื•ืจื›ื‘
01:37
billions of active neurons,
35
97260
2000
ืžืžื™ืœื™ืืจื“ื™ ื ื•ื™ืจื•ื ื™ื ืคืขื™ืœื™ื,
01:39
around 170,000 km
36
99260
3000
ื‘ืขืจืš 170,000 ืง"ืž
01:42
of combined axon length.
37
102260
2000
ืฉืœ ืืงืกื•ื ื™ื ืžืฉื•ืœื‘ื™ื.
01:44
When these neurons interact,
38
104260
2000
ื›ืืฉืจ ื ื•ืฆืจืช ืื™ื ื˜ืจืืงืฆื™ื” ื‘ื™ืŸ ื”ื ื™ื•ืจื•ื ื™ื ื”ืœืœื•,
01:46
the chemical reaction emits an electrical impulse,
39
106260
2000
ื”ืชื’ื•ื‘ื” ื”ื›ื™ืžื™ืช ืžืคื™ืฆื” ืคื•ืœืก ื—ืฉืžืœื™
01:48
which can be measured.
40
108260
2000
ืื•ืชื• ื ื™ืชืŸ ืœืžื“ื•ื“.
01:50
The majority of our functional brain
41
110260
3000
ืจื•ื‘ื• ืฉืœ ื”ืžื•ื— ื”ืคืขื™ืœ ืฉืœื ื•
01:53
is distributed over
42
113260
2000
ื ืžืฆื ื‘ืื™ื–ื•ืจ
01:55
the outer surface layer of the brain,
43
115260
2000
ืžืฉื˜ื— ื”ืฉื›ื‘ื” ื”ื—ื™ืฆื•ื ื™ืช ืฉืœ ื”ืžื•ื— ืฉืœื ื•.
01:57
and to increase the area that's available for mental capacity,
44
117260
3000
ื•ืขืœ ืžื ืช ืœื”ื’ื“ื™ืœ ืืช ื”ืฉื˜ื— ื”ืงื™ื™ื ืœื™ื›ื•ืœื•ืช ืžื ื˜ืœื™ื•ืช,
02:00
the brain surface is highly folded.
45
120260
3000
ืžืฉื˜ื— ื”ืžื•ื— ืžืงื•ืคืœ ื‘ื™ื•ืชืจ.
02:03
Now this cortical folding
46
123260
2000
ื›ืขืช, ื”ืงื™ืคื•ืœ ื”ืžื•ื—ื™ ื”ื–ื”
02:05
presents a significant challenge
47
125260
2000
ืžืฆื™ื’ ืืชื’ืจ ืžืฉืžืขื•ืชื™
02:07
for interpreting surface electrical impulses.
48
127260
3000
ื‘ืคื™ืขื ื•ื— ืคื•ืœืกื™ื ื—ืฉืžืœื™ื™ื.
02:10
Each individual's cortex
49
130260
2000
ื”ืงืœื™ืคื” ื”ืžื•ื—ื™ืช ืฉืœ ื›ืœ ืื“ื
02:12
is folded differently,
50
132260
2000
ืžืงื•ืคืœืช ื‘ืื•ืคืŸ ืฉื•ื ื”,
02:14
very much like a fingerprint.
51
134260
2000
ื‘ื“ื•ืžื” ืžืื•ื“ ืœื˜ื‘ื™ืขืช ืืฆื‘ืข.
02:16
So even though a signal
52
136260
2000
ื›ืš ืฉืœืžืจื•ืช ืฉืื•ืช
02:18
may come from the same functional part of the brain,
53
138260
3000
ื™ื›ื•ืœ ืœื”ื’ื™ืข ืžื—ืœืง ื“ื•ืžื” ื‘ืžื•ื— ื”ืคืขื™ืœ,
02:21
by the time the structure has been folded,
54
141260
2000
ื‘ื–ืžืŸ ืฉื”ืžื‘ื ื” ื”ืชืงืคืœ,
02:23
its physical location
55
143260
2000
ื”ืžื™ืงื•ื ื”ืคื™ื–ื™ ืฉืœื•
02:25
is very different between individuals,
56
145260
2000
ืฉื•ื ื” ืžืื•ื“ ื‘ื™ืŸ ืื“ื ืœืื“ื,
02:27
even identical twins.
57
147260
3000
ืืคื™ืœื• ื‘ืชืื•ืžื™ื ื–ื”ื™ื.
02:30
There is no longer any consistency
58
150260
2000
ื›ื‘ืจ ืื™ืŸ ืื—ื™ื“ื•ืช
02:32
in the surface signals.
59
152260
2000
ื‘ืื•ืชื•ืช ืขืœ ืคื ื™ ื”ืฉื˜ื—.
02:34
Our breakthrough was to create an algorithm
60
154260
2000
ืคืจื™ืฆืช ื”ื“ืจืš ืฉืœื ื• ื”ื™ื™ืชื” ื‘ื™ืฆื™ืจืช ืืœื’ื•ืจื™ืชื
02:36
that unfolds the cortex,
61
156260
2000
ืืฉืจ ืคื•ืชื— ืืช ืงื™ืคื•ืœื™ ื”ืงืœื™ืคื” ื”ืžื•ื—ื™ืช,
02:38
so that we can map the signals
62
158260
2000
ื›ืš ืฉืื ื• ื™ื›ื•ืœื™ื ืœืžืคื•ืช ืืช ื”ืื•ืชื•ืช
02:40
closer to its source,
63
160260
2000
ืงืจื•ื‘ ื™ื•ืชืจ ืœืžืงื•ืจ ืฉืœื”ื,
02:42
and therefore making it capable of working across a mass population.
64
162260
3000
ื•ื‘ื›ืš ืžืืคืฉืจื™ื ืœืžืขืจื›ืช ืœืขื‘ื•ื“ ืขื ืื•ื›ืœื•ืกื™ื” ื’ื“ื•ืœื”.
02:46
The second challenge
65
166260
2000
ื”ืืชื’ืจ ื”ืฉื ื™
02:48
is the actual device for observing brainwaves.
66
168260
3000
ื”ื•ื ื”ืžื›ืฉื™ืจ ืขืฆืžื• ืœืฆืคื™ื™ื” ื‘ื’ืœื™ ื”ืžื•ื—
02:51
EEG measurements typically involve
67
171260
2000
ืžื“ื™ื“ื•ืช EEG ื‘ื“ืจืš ื›ืœืœ ื›ื•ืœืœื•ืช
02:53
a hairnet with an array of sensors,
68
173260
3000
ืจืฉืช ืฉื™ืขืจ ืขื ืžืขืจืš ืฉืœ ื—ื™ื™ืฉื ื™ื,
02:56
like the one that you can see here in the photo.
69
176260
3000
ื›ืžื• ื–ื• ืฉืืชื ื™ื›ื•ืœื™ื ืœืจืื•ืช ื›ืืŸ ื‘ืชืžื•ื ื”.
02:59
A technician will put the electrodes
70
179260
2000
ื˜ื›ื ืื™ ืฉื ืืช ื”ืืœืงื˜ืจื•ื“ื•ืช
03:01
onto the scalp
71
181260
2000
ืขืœ ื”ืงืจืงืคืช
03:03
using a conductive gel or paste
72
183260
2000
ื‘ืืžืฆืขื•ืช ื’'ืœ ืžื•ืœื™ืš ืื• ืžืฉื—ื”
03:05
and usually after a procedure of preparing the scalp
73
185260
3000
ื•ืœืจื•ื‘ ืœืื—ืจ ืชื”ืœื™ืš ืฉืœ ื”ื›ื ืช ื”ืงืจืงืคืช
03:08
by light abrasion.
74
188260
2000
ืข"ื™ ืฉืคืฉื•ืฃ ืงืœ.
03:10
Now this is quite time consuming
75
190260
2000
ื›ืขืช, ื–ื”ื• ืชื”ืœื™ืš ื”ืฆื•ืจืš ื–ืžืŸ ืžื”
03:12
and isn't the most comfortable process.
76
192260
2000
ื•ื’ื ืœื ืžืื•ื“ ื ื•ื—.
03:14
And on top of that, these systems
77
194260
2000
ื•ื‘ื ื•ืกืฃ, ืžืขืจื›ื•ืช ืืœื•
03:16
actually cost in the tens of thousands of dollars.
78
196260
3000
ืœืžืขืฉื” ืขื•ืœื•ืช ืขืฉืจื•ืช ืืœืคื™ ื“ื•ืœืจื™ื.
03:20
So with that, I'd like to invite onstage
79
200260
3000
ืื– ืขื ื–ื”, ื”ื™ื™ืชื™ ืžืขื•ื ื™ื™ื ืช ืœื”ื–ืžื™ืŸ ืœื‘ืžื” ืืช
03:23
Evan Grant, who is one of last year's speakers,
80
203260
2000
ืื•ื•ืŸ ื’ืจืื ื˜, ืื—ื“ ืžื”ื“ื•ื‘ืจื™ื ืฉืœ ืฉื ื” ืฉืขื‘ืจื”.
03:25
who's kindly agreed
81
205260
2000
ืืฉืจ ื”ืกื›ื™ื ื‘ืื“ื™ื‘ื•ืชื•
03:27
to help me to demonstrate
82
207260
2000
ืœืขื–ื•ืจ ืœื™ ืœื”ื“ื’ื™ื
03:29
what we've been able to develop.
83
209260
2000
ืืช ืžื” ืฉื”ืฆืœื—ื ื• ืœืคืชื—.
03:31
(Applause)
84
211260
6000
(ืžื—ื™ืื•ืช ื›ืคื™ื™ื)
03:37
So the device that you see
85
217260
2000
ืื– ื”ืžื›ืฉื™ืจ ืฉืืชื ืจื•ืื™ื
03:39
is a 14-channel, high-fidelity
86
219260
2000
ื”ื•ื ื‘ืขืœ 14 ืขืจื•ืฆื™ื, ื•ื™ื›ื•ืœืช ื’ื‘ื•ื”ื”
03:41
EEG acquisition system.
87
221260
2000
ืœืงืœื™ื˜ืช EEG.
03:43
It doesn't require any scalp preparation,
88
223260
3000
ื”ื•ื ืื™ื ื• ื“ื•ืจืฉ ื”ื›ื ื” ืžื•ืงื“ืžืช ืฉืœ ื”ืงืจืงืคืช,
03:46
no conductive gel or paste.
89
226260
2000
ื•ื’ื ืœื ื’'ืœ ื›ืžื•ืœื™ืš ืื• ืžืฉื—ื”.
03:48
It only takes a few minutes to put on
90
228260
3000
ืœื•ืงื— ื“ืงื•ืช ื‘ื•ื“ื“ื•ืช ืœื”ืœื‘ื™ืฉ ืื•ืชื•
03:51
and for the signals to settle.
91
231260
2000
ื•ืœื”ืชื—ื™ืœ ืœืงืœื•ื˜ ืืช ื”ื’ืœื™ื.
03:53
It's also wireless,
92
233260
2000
ื”ื•ื ื’ื ืืœื—ื•ื˜ื™,
03:55
so it gives you the freedom to move around.
93
235260
3000
ื›ืš ืฉื”ื•ื ืžืืคืฉืจ ืœืš ืœื ื•ืข ื‘ื—ื•ืคืฉื™ื•ืช.
03:58
And compared to the tens of thousands of dollars
94
238260
3000
ื•ื‘ื”ืฉื•ื•ืื” ืœืขืฉืจื•ืช ื”ืืœืคื™ื ืฉืœ ื“ื•ืœืจื™ื
04:01
for a traditional EEG system,
95
241260
3000
ืœืžืขืจื›ืช EEG ืžืกื•ืจืชื™ืช,
04:04
this headset only costs
96
244260
2000
ื”ืชืงืŸ ื”ืจืืฉ ื”ื–ื” ืขื•ืœื”
04:06
a few hundred dollars.
97
246260
2000
ื›ืžื” ืžืื•ืช ื“ื•ืœืจื™ื ื‘ืœื‘ื“.
04:08
Now on to the detection algorithms.
98
248260
3000
ืขื›ืฉื™ื• ื ืขื‘ื•ืจ ืœืืœื’ื•ืจื™ืชืžื™ื ืฉืœ ื”ื–ื™ื”ื•ื™.
04:11
So facial expressions --
99
251260
2000
ืื– ื”ื‘ืขื•ืช ืคื ื™ื -
04:13
as I mentioned before in emotional experiences --
100
253260
2000
ื›ืžื• ืฉื”ืกื‘ืจืชื™ ืžืงื•ื“ื ื‘ื”ื‘ืขื•ืช ืจื’ืฉื™ื•ืช --
04:15
are actually designed to work out of the box
101
255260
2000
ืœืžืขืฉื” ืžืชื•ื›ื ื ื•ืช ืœืขื‘ื•ื“ ื‘ืื•ืคืŸ ื˜ื‘ืขื™
04:17
with some sensitivity adjustments
102
257260
2000
ืขื ื›ืžื” ืฉื™ื ื•ื™ื™ื ื‘ืจื’ื™ืฉื•ืช
04:19
available for personalization.
103
259260
3000
ื”ืงื™ื™ืžื™ื ืœืฆื•ืจืš ื”ืชืืžื” ืื™ืฉื™ืช.
04:22
But with the limited time we have available,
104
262260
2000
ืืš ื‘ืฉืœ ื”ื–ืžืŸ ื”ืงืฆืจ ื”ืขื•ืžื“ ืœืจืฉื•ืชื ื•,
04:24
I'd like to show you the cognitive suite,
105
264260
2000
ื”ื™ื™ืชื™ ืจื•ืฆื” ืœื”ืฆื™ื’ ื‘ืคื ื™ื›ื ืืช ื”ื—ื‘ื™ืœื” ื”ืงื•ื’ื ื™ื˜ื™ื‘ื™ืช,
04:26
which is the ability for you
106
266260
2000
ืืฉืจ ืžืืคืฉืจืช ืœืš
04:28
to basically move virtual objects with your mind.
107
268260
3000
ืœื”ื–ื™ื– ื—ืคืฆื™ื ื•ื™ืจื˜ื•ืืœื™ื ื‘ืขื–ืจืช ื”ืžื—ืฉื‘ื”.
04:32
Now, Evan is new to this system,
108
272260
2000
ื›ืขืช, ืื•ื•ืŸ ื—ื“ืฉ ื‘ืžืขืจื›ืช,
04:34
so what we have to do first
109
274260
2000
ืื– ืžื” ืฉืื ื• ืฆืจื™ื›ื™ื ืœืขืฉื•ืช ืชื—ื™ืœื”
04:36
is create a new profile for him.
110
276260
2000
ื”ื•ื ืœื™ืฆื•ืจ ืคืจื•ืคื™ืœ ื—ื“ืฉ ืขื‘ื•ืจื•.
04:38
He's obviously not Joanne -- so we'll "add user."
111
278260
3000
ื”ื•ื ื‘ื•ื•ื“ืื™ ืœื ื’'ื•ืืŸ -- ืื– ืื ื—ื ื• "ื ื•ืกื™ืฃ ืžืฉืชืžืฉ".
04:41
Evan. Okay.
112
281260
2000
ืื•ื•ืŸ. ื‘ืกื“ืจ.
04:43
So the first thing we need to do with the cognitive suite
113
283260
3000
ืื– ื”ื“ื‘ืจ ื”ืจืืฉื•ืŸ ืฉืื ื—ื ื• ืฆืจื™ื›ื™ื ืœืขืฉื•ืช ืขื ื”ื—ื‘ื™ืœื” ื”ืงื•ื’ื ื™ื˜ื™ื‘ื™ืช
04:46
is to start with training
114
286260
2000
ื”ื•ื ืœื”ืชื—ื™ืœ ืขื ืื™ืžื•ืŸ
04:48
a neutral signal.
115
288260
2000
ืฉืœ ืื•ืช ื ื™ื˜ืจืœื™.
04:50
With neutral, there's nothing in particular
116
290260
2000
ืขื ื ื™ื˜ืจืœื™, ืื™ืŸ ืžืฉื”ื• ืžื™ื•ื—ื“
04:52
that Evan needs to do.
117
292260
2000
ืฉืื•ื•ืŸ ืฆืจื™ืš ืœืขืฉื•ืช.
04:54
He just hangs out. He's relaxed.
118
294260
2000
ื”ื•ื ืจืง ืขื•ืžื“. ื”ื•ื ืจื’ื•ืข.
04:56
And the idea is to establish a baseline
119
296260
2000
ื•ื”ืจืขื™ื•ืŸ ื”ื•ื ืœื”ื’ื“ื™ืจ ื‘ืกื™ืก
04:58
or normal state for his brain,
120
298260
2000
ืื• ืžืฆื‘ ื ื•ืจืžืœื™ ืœืžื•ื— ืฉืœื•.
05:00
because every brain is different.
121
300260
2000
ืžื›ื™ื•ื•ืŸ ืฉื›ืœ ืžื•ื— ื”ื•ื ืฉื•ื ื”.
05:02
It takes eight seconds to do this,
122
302260
2000
ื–ื” ืœื•ืงื— 8 ืฉื ื™ื•ืช ืœื‘ื™ืฆื•ืข ื”ืคืขื•ืœื”.
05:04
and now that that's done,
123
304260
2000
ื•ืขื›ืฉื™ื• ืฉื–ื” ื ื’ืžืจ,
05:06
we can choose a movement-based action.
124
306260
2000
ืื ื• ื™ื›ื•ืœื™ื ืœื‘ื—ื•ืจ ืคืขื•ืœื” ืžื‘ื•ืกืกืช ืชื ื•ืขื”.
05:08
So Evan, choose something
125
308260
2000
ืื– ืื•ื•ืŸ ืชื‘ื—ืจ ืžืฉื”ื•
05:10
that you can visualize clearly in your mind.
126
310260
2000
ืื•ืชื• ืืชื” ื™ื›ื•ืœ ืœื“ืžื™ื™ืŸ ื‘ื‘ื”ื™ืจื•ืช ื‘ืžื•ื—ืš.
05:12
Evan Grant: Let's do "pull."
127
312260
2000
ืื•ื•ืŸ ื’ืจื ื˜: ื‘ื•ืื™ ื ื‘ืฆืข "ืžืฉื™ื›ื”".
05:14
Tan Le: Okay, so let's choose "pull."
128
314260
2000
ื˜ืืŸ ืœื”: ื‘ืกื“ืจ. ืื– ื‘ื•ื ื ื‘ื—ืจ "ืžืฉื™ื›ื”".
05:16
So the idea here now
129
316260
2000
ืื– ื”ืจืขื™ื•ืŸ ื›ืืŸ ื”ื•ื
05:18
is that Evan needs to
130
318260
2000
ืฉืื•ื•ืŸ ืฆืจื™ืš
05:20
imagine the object coming forward
131
320260
2000
ืœื“ืžื™ื™ืŸ ืืช ื”ืื•ื‘ื™ื™ืงื˜ ืžืชืงื“ื
05:22
into the screen,
132
322260
2000
ืœืชื•ืš ื”ืžืกืš.
05:24
and there's a progress bar that will scroll across the screen
133
324260
3000
ื•ื™ืฉ ืžื“ ื”ืชืงื“ืžื•ืช ืœืื•ืจื›ื• ืฉืœ ื”ืžืกืš
05:27
while he's doing that.
134
327260
2000
ื‘ื–ืžืŸ ืฉื”ื•ื ืขื•ืฉื” ืืช ื–ื”.
05:29
The first time, nothing will happen,
135
329260
2000
ื‘ืคืขื ื”ืจืืฉื•ื ื”, ืฉื•ื ื“ื‘ืจ ืœื ื™ืงืจื”,
05:31
because the system has no idea how he thinks about "pull."
136
331260
3000
ืžื›ื™ื•ื•ืŸ ื•ื”ืžืขืจื›ืช ืœื ื™ื•ื“ืขืช ืื™ืš ื”ื•ื ื—ื•ืฉื‘ ืขืœ "ืžืฉื™ื›ื”".
05:34
But maintain that thought
137
334260
2000
ืื‘ืœ ืชืฉืžื•ืจ ืขืœ ื”ืžื—ืฉื‘ื” ื”ื–ื•
05:36
for the entire duration of the eight seconds.
138
336260
2000
ืœืžืฉืš ื›ืœ ื”-8 ืฉื ื™ื•ืช.
05:38
So: one, two, three, go.
139
338260
3000
ืื–: ืื—ืช, ืฉืชื™ื™ื, ืฉืœื•ืฉ ื•ื–ื”ื•.
05:49
Okay.
140
349260
2000
ื‘ืกื“ืจ.
05:51
So once we accept this,
141
351260
2000
ืื– ื‘ืจื’ืข ืฉืื ื• ืžืืฉืจื™ื ืืช ื–ื”,
05:53
the cube is live.
142
353260
2000
ื”ืงื•ื‘ื™ื” ื—ื™ื”.
05:55
So let's see if Evan
143
355260
2000
ืื– ื‘ื•ืื• ื ืจืื” ื”ืื ืื•ื•ืŸ
05:57
can actually try and imagine pulling.
144
357260
3000
ืœืžืขืฉื” ื™ื›ื•ืœ ืœื ืกื•ืช ื•ืœื“ืžื™ื™ืŸ ืžืฉื™ื›ื”.
06:00
Ah, good job!
145
360260
2000
ืื”, ืขื‘ื•ื“ื” ื˜ื•ื‘ื”.
06:02
(Applause)
146
362260
3000
(ืžื—ื™ืื•ืช ื›ืคื™ื™ื)
06:05
That's really amazing.
147
365260
2000
ื–ื” ืœืžืขืฉื” ืžื“ื”ื™ื.
06:07
(Applause)
148
367260
4000
(ืžื—ื™ืื•ืช ื›ืคื™ื™ื)
06:11
So we have a little bit of time available,
149
371260
2000
ืื– ื™ืฉ ืœื ื• ืžืขื˜ ื–ืžืŸ ืคื ื•ื™,
06:13
so I'm going to ask Evan
150
373260
2000
ืœื›ืŸ ืื‘ืงืฉ ืžืื•ื•ืŸ
06:15
to do a really difficult task.
151
375260
2000
ืœื‘ืฆืข ืžืฉื™ืžื” ืงืฉื” ื‘ืžื™ื•ื—ื“.
06:17
And this one is difficult
152
377260
2000
ื•ื–ื• ืงืฉื”
06:19
because it's all about being able to visualize something
153
379260
3000
ืžื›ื™ื•ื•ืŸ ืฉื”ื™ื ื›ืจื•ื›ื” ื‘ื™ื›ื•ืœืช ืœื“ืžื™ื™ืŸ ืžืฉื”ื•
06:22
that doesn't exist in our physical world.
154
382260
2000
ืฉืœื ืงื™ื™ื ื‘ืขื•ืœื ื”ืคื™ื–ื™.
06:24
This is "disappear."
155
384260
2000
ื–ื” "ื”ื™ืขืœืžื•ืช".
06:26
So what you want to do -- at least with movement-based actions,
156
386260
2000
ืื– ืžื” ืฉืืชื” ืจื•ืฆื” -- ืœืคื—ื•ืช ืขื ืคืขื•ืœื•ืช ืžื‘ื•ืกืกื•ืช ืชื ื•ืขื”,
06:28
we do that all the time, so you can visualize it.
157
388260
3000
ืื ื• ืขื•ืฉื™ื ืืช ื–ื” ื›ืœ ื”ื–ืžืŸ, ื›ืš ืฉืืชื” ื™ื›ื•ืœ ืœื“ืžื™ื™ืŸ ืืช ื–ื”.
06:31
But with "disappear," there's really no analogies --
158
391260
2000
ืื‘ืœ ืขื "ื”ื™ืขืœืžื•ืช", ืื™ืŸ ืžืžืฉ ืื ืœื•ื’ื™ื•ืช.
06:33
so Evan, what you want to do here
159
393260
2000
ืื– ืื•ื•ืŸ, ืžื” ืฉืืชื” ืจื•ืฆื” ืœืขืฉื•ืช ื›ืืŸ
06:35
is to imagine the cube slowly fading out, okay.
160
395260
3000
ื”ื•ื ืœื“ืžื™ื™ืŸ ืืช ื”ืงื•ื‘ื™ื” ื ืขืœืžืช ื‘ื”ื“ืจื’ื”, ื‘ืกื“ืจ.
06:38
Same sort of drill. So: one, two, three, go.
161
398260
3000
ืื•ืชื• ืชื”ืœื™ืš ื›ืžื• ืžืงื•ื“ื. ืื–: ืื—ืช, ืฉืชื™ื™ื, ืฉืœื•ืฉื” ื•ื–ื”ื•.
06:50
Okay. Let's try that.
162
410260
3000
ื‘ืกื“ืจ. ื‘ื•ื ื ื ืกื” ืืช ื–ื”.
06:53
Oh, my goodness. He's just too good.
163
413260
3000
ื”ื•, ืื™ื–ื” ื™ื•ืคื™. ื”ื•ื ืคืฉื•ื˜ ื˜ื•ื‘ ืžื™ื“ื™.
06:57
Let's try that again.
164
417260
2000
ื‘ื•ื ื ื ืกื” ื–ืืช ืฉื•ื‘.
07:04
EG: Losing concentration.
165
424260
2000
ืื•ื•ืŸ ื’ืจื ื˜: ืžืื‘ื“ ืจื™ื›ื•ื–.
07:06
(Laughter)
166
426260
2000
(ืฆื—ื•ืง)
07:08
TL: But we can see that it actually works,
167
428260
2000
ื˜ืืŸ ืœื”: ืื‘ืœ ืื ื—ื ื• ื™ื›ื•ืœื™ื ืœืจืื•ืช ืฉื–ื” ืžืžืฉ ืขื•ื‘ื“.
07:10
even though you can only hold it
168
430260
2000
ืืคื™ืœื• ืฉืืชื” ื‘ืงื•ืฉื™ ืžื—ื–ื™ืง ืืช ื–ื”
07:12
for a little bit of time.
169
432260
2000
ืœื–ืžืŸ ืงืฆืจ ืžืื•ื“.
07:14
As I said, it's a very difficult process
170
434260
3000
ื›ืžื• ืฉืืžืจืชื™, ื–ื”ื• ืชื”ืœื™ืš ืงืฉื” ื‘ืžื™ื•ื—ื“
07:17
to imagine this.
171
437260
2000
ืœื“ืžื™ื™ืŸ ืืช ื–ื”.
07:19
And the great thing about it is that
172
439260
2000
ื•ื”ื“ื‘ืจ ื”ื’ื“ื•ืœ ื‘ื ื•ื’ืข ืœื–ื” ื”ื•ื
07:21
we've only given the software one instance
173
441260
2000
ื ืชื ื• ืœืชื•ื›ื ื” ืจืง ืžื•ืคืข ืื—ืช
07:23
of how he thinks about "disappear."
174
443260
3000
ืฉืœ ืื™ืš ืฉื”ื•ื ื—ื•ืฉื‘ ืขืœ "ื”ื™ืขืœืžื•ืช".
07:26
As there is a machine learning algorithm in this --
175
446260
3000
ื›ืš ืฉื™ืฉ ืืœื’ื•ืจื™ืชื ืžื›ื•ื ื” ืœืœื™ืžื•ื“ ื‘ืชื•ืš ื–ื” --
07:29
(Applause)
176
449260
4000
(ืžื—ื™ืื•ืช ื›ืคื™ื™ื)
07:33
Thank you.
177
453260
2000
ืชื•ื“ื” ืœืš.
07:35
Good job. Good job.
178
455260
3000
ืขื‘ื•ื“ื” ื˜ื•ื‘ื”. ืขื‘ื•ื“ื” ื˜ื•ื‘ื”.
07:38
(Applause)
179
458260
2000
(ืžื—ื™ืื•ืช ื›ืคื™ื™ื)
07:40
Thank you, Evan, you're a wonderful, wonderful
180
460260
3000
ืชื•ื“ื” ืœืš, ืื•ื•ืŸ, ืืชื” ื“ื•ื’ืžื ื ืคืœืื”, ื ืคืœืื”
07:43
example of the technology.
181
463260
3000
ืฉืœ ื”ื˜ื›ื ื•ืœื•ื’ื™ื”.
07:46
So, as you can see, before,
182
466260
2000
ืื– ื›ืžื• ืฉื™ื›ื•ืœืชื ืœืจืื•ืช ืžืงื•ื“ื,
07:48
there is a leveling system built into this software
183
468260
3000
ื™ืฉ ืžืขืจื›ืช ืื™ื–ื•ืŸ ื”ื‘ื ื•ื™ื” ื‘ืชื•ืš ื”ืชื•ื›ื ื”
07:51
so that as Evan, or any user,
184
471260
2000
ื›ืš ืฉื‘ืขืช ืฉืื•ื•ืŸ, ืื• ื›ืœ ืžืฉืชืžืฉ,
07:53
becomes more familiar with the system,
185
473260
2000
ืžื›ื™ืจื™ื ืืช ื”ืžืขืจื›ืช ื˜ื•ื‘ ื™ื•ืชืจ,
07:55
they can continue to add more and more detections,
186
475260
3000
ื”ื ื™ื›ื•ืœื™ื ืœื”ืžืฉื™ืš ื•ืœื”ื•ืกื™ืฃ ืขื•ื“ ื•ืขื•ื“ ื–ื™ื”ื•ื™,
07:58
so that the system begins to differentiate
187
478260
2000
ื›ืš ืฉื”ืžืขืจื›ืช ืžืชื—ื™ืœื” ืœื”ื‘ื—ื™ืŸ
08:00
between different distinct thoughts.
188
480260
3000
ื‘ื™ืŸ ืžื—ืฉื‘ื•ืช ื™ื™ื—ื•ื“ื™ื•ืช ืฉื•ื ื•ืช
08:04
And once you've trained up the detections,
189
484260
2000
ื•ื‘ืจื’ืข ืฉืืชื” ืžืืžืŸ ืืช ื”ื”ื‘ื—ื ื•ืช,
08:06
these thoughts can be assigned or mapped
190
486260
2000
ื”ืžื—ืฉื‘ื•ืช ื”ืืœื• ื™ื›ื•ืœื•ืช ืœื”ื™ื•ืช ืžื•ื’ื“ืจื•ืช ืื• ืžืžื•ืคื•ืช
08:08
to any computing platform,
191
488260
2000
ืœื›ืœ ืคืœื˜ืคื•ืจืžืช ืžื—ืฉื‘,
08:10
application or device.
192
490260
2000
ืชื•ื›ื ื” ืื• ืžื›ืฉื™ืจ.
08:12
So I'd like to show you a few examples,
193
492260
2000
ืื– ื”ื™ื™ืชื™ ืจื•ืฆื” ืœื”ืฆื™ื’ ื‘ืคื ื™ื›ื ืžืกืคืจ ื“ื•ื’ืžืื•ืช,
08:14
because there are many possible applications
194
494260
2000
ืžื›ื™ื•ื•ืŸ ื•ื™ืฉื ื ื™ื™ืฉื•ืžื™ื ืจื‘ื™ื ืืคืฉืจื™ื™ื
08:16
for this new interface.
195
496260
2000
ืœืžืžืฉืง ื”ื—ื“ืฉ ื”ื–ื”.
08:19
In games and virtual worlds, for example,
196
499260
2000
ื‘ืžืฉื—ืงื™ื ื•ืขื•ืœืžื•ืช ืžื“ื•ืžื™ื, ืœื“ื•ื’ืžื,
08:21
your facial expressions
197
501260
2000
ื”ื‘ืขื•ืช ื”ืคื ื™ื ืฉืœื›ื
08:23
can naturally and intuitively be used
198
503260
2000
ื™ื›ื•ืœื•ืช ื‘ืื•ืคืŸ ื˜ื‘ืขื™ ื•ืื™ื ื˜ื•ืื™ื˜ื™ื‘ื™ ืœืฉืžืฉ
08:25
to control an avatar or virtual character.
199
505260
3000
ืœืฉืœื™ื˜ื” ื‘ื“ืžื•ืช ืื• ื‘ื™ืฆื•ืจ ื•ื™ืจื˜ื•ืืœื™.
08:29
Obviously, you can experience the fantasy of magic
200
509260
2000
ืืชื ื™ื›ื•ืœื™ื ืœื—ื•ื•ืช ืืช ื”ื ืคืœืื•ืช ืฉืœ ื”ืงืกื
08:31
and control the world with your mind.
201
511260
3000
ื•ืœืฉืœื•ื˜ ื‘ืขื•ืœื ืขื ื”ืžื•ื— ืฉืœื›ื.
08:36
And also, colors, lighting,
202
516260
3000
ื•ื’ื, ืฆื‘ืขื™ื, ืื•ืจื•ืช,
08:39
sound and effects
203
519260
2000
ืฆืœื™ืœื™ื ื•ืืคืงื˜ื™ื,
08:41
can dynamically respond to your emotional state
204
521260
2000
ื™ื›ื•ืœื™ื ื‘ืื•ืคืŸ ื“ื™ื ืืžื™ ืœื”ื’ื™ื‘ ืœืžืฆื‘ ื”ืจื™ื’ืฉื™ ืฉืœืš
08:43
to heighten the experience that you're having, in real time.
205
523260
3000
ืœื”ืขืฆื™ื ืืช ื”ื—ื•ื•ื™ื” ืฉืœืš, ื‘ื–ืžืŸ ืืžืช.
08:47
And moving on to some applications
206
527260
2000
ื•ื ืขื‘ื•ืจ ืœืžืกืคืจ ื™ื™ืฉื•ืžื™ื
08:49
developed by developers and researchers around the world,
207
529260
3000
ืฉืคื•ืชื—ื• ืข"ื™ ืžืคืชื—ื™ื ื•ื—ื•ืงืจื™ื ืžืจื—ื‘ื™ ื”ืขื•ืœื,
08:52
with robots and simple machines, for example --
208
532260
3000
ื‘ืขื–ืจืช ืจื•ื‘ื•ื˜ื™ื ื•ืžื›ื•ื ื•ืช ืคืฉื•ื˜ื•ืช, ืœื“ื•ื’ืžื --
08:55
in this case, flying a toy helicopter
209
535260
2000
ื‘ืžืงืจื” ื”ื–ื”, ื”ื˜ืกืช ืžืกื•ืง ืฆืขืฆื•ืข
08:57
simply by thinking "lift" with your mind.
210
537260
3000
ืคืฉื•ื˜ ื‘ืืžืฆืขื•ืช ื”ืžื—ืฉื‘ื” ืฉืœ ืœื”ืจื™ื ืื•ืชื•.
09:00
The technology can also be applied
211
540260
2000
ื”ื˜ื›ื ื•ืœื•ื’ื™ื” ื™ื›ื•ืœื” ืœื”ื™ื•ืช ืžื™ื•ืฉืžืช ื’ื
09:02
to real world applications --
212
542260
2000
ืœื™ื™ืฉื•ืžื™ื ื‘ืขื•ืœื ื”ืืžื™ืชื™ --
09:04
in this example, a smart home.
213
544260
2000
ื‘ืžืงืจื” ื”ื–ื”, ื‘ื™ืช ื—ื›ื.
09:06
You know, from the user interface of the control system
214
546260
3000
ืืชื ื™ื•ื“ืขื™ื, ืžืžืžืฉืง ื”ืžืฉืชืžืฉ ืฉืœ ืžืขืจื›ืช ื”ืฉืœื™ื˜ื”
09:09
to opening curtains
215
549260
2000
ืœืคืชื™ื—ืช ื•ื™ืœื•ื ื•ืช
09:11
or closing curtains.
216
551260
3000
ืื• ืกื’ื™ืจืชื.
09:22
And of course, also to the lighting --
217
562260
3000
ื•ื‘ื•ื•ื“ืื™ ืฉื’ื ืœืื•ืจื•ืช --
09:25
turning them on
218
565260
3000
ืœื”ื“ืœื™ืง
09:28
or off.
219
568260
2000
ืื• ืœื›ื‘ื•ืช ืื•ืชื.
09:30
And finally,
220
570260
2000
ื•ืœื‘ืกื•ืฃ,
09:32
to real life-changing applications,
221
572260
2000
ืœื™ื™ืฉื•ืžื™ื ืืžื™ืชื™ื™ื ืžืฉื ื™-ื—ื™ื™ื
09:34
such as being able to control an electric wheelchair.
222
574260
3000
ื›ืžื• ื”ื™ื›ื•ืœืช ืœืฉืœื•ื˜ ื‘ื›ื™ืกื ื’ืœื’ืœื™ื ื—ืฉืžืœื™.
09:37
In this example,
223
577260
2000
ื‘ืžืงืจื” ื”ื–ื”,
09:39
facial expressions are mapped to the movement commands.
224
579260
3000
ื”ื‘ืขื•ืช ื”ืคื ื™ื ืžืžื•ืคื•ืช ืœืคืงื•ื“ื•ืช ื”ืชื ื•ืขื”.
09:42
Man: Now blink right to go right.
225
582260
3000
ืื“ื: "ืขื›ืฉื™ื• ืžืฆืžืฅ ื‘ืขื™ืŸ ื™ืžื™ืŸ ืœื–ื•ื– ื™ืžื™ื ื”".
09:50
Now blink left to turn back left.
226
590260
3000
"ืขื›ืฉื™ื• ืžืฆืžืฅ ื‘ืขื™ืŸ ืฉืžืืœ ืœื–ื•ื– ืฉืžืืœื”".
10:02
Now smile to go straight.
227
602260
3000
"ืขื›ืฉื™ื• ื—ื™ื™ืš ืœื–ื•ื– ืงื“ื™ืžื”".
10:08
TL: We really -- Thank you.
228
608260
2000
ื˜ื™ ืืœ: ืื ื• ื‘ืืžืช -- ืžื•ื“ื™ื ืœืš.
10:10
(Applause)
229
610260
5000
(ืžื—ื™ืื•ืช ื›ืคื™ื™ื)
10:15
We are really only scratching the surface of what is possible today,
230
615260
3000
ืื ื• ื‘ืืžืช ืจืง ืžื’ืจื“ื™ื ืืช ืคื ื™ ื”ืฉื˜ื— ืฉืœ ื”ืืคืฉืจื™ ื›ื™ื•ื.
10:18
and with the community's input,
231
618260
2000
ื•ืขื ืžืฉื•ื‘ื™ื ืžื”ืงื”ื™ืœื”,
10:20
and also with the involvement of developers
232
620260
2000
ื•ืขื ื”ืžืขื•ืจื‘ื•ืช ืฉืœ ืžืคืชื—ื™ื
10:22
and researchers from around the world,
233
622260
3000
ื•ื—ื•ืงืจื™ื ืžืจื—ื‘ื™ ื”ืขื•ืœื,
10:25
we hope that you can help us to shape
234
625260
2000
ืื ื• ืžืงื•ื•ื™ื ืฉืืชื ื™ื›ื•ืœื™ื ืœืขื–ื•ืจ ืœื ื• ืœืขืฆื‘
10:27
where the technology goes from here. Thank you so much.
235
627260
3000
ืืช ื›ื™ื•ื•ื ื” ืฉืœ ื”ื˜ื›ื ื•ืœื•ื’ื™ื” ืžื›ืืŸ. ืชื•ื“ื” ืจื‘ื” ืœื›ื.
ืขืœ ืืชืจ ื–ื”

ืืชืจ ื–ื” ื™ืฆื™ื’ ื‘ืคื ื™ื›ื ืกืจื˜ื•ื ื™ YouTube ื”ืžื•ืขื™ืœื™ื ืœืœื™ืžื•ื“ ืื ื’ืœื™ืช. ืชื•ื›ืœื• ืœืจืื•ืช ืฉื™ืขื•ืจื™ ืื ื’ืœื™ืช ื”ืžื•ืขื‘ืจื™ื ืขืœ ื™ื“ื™ ืžื•ืจื™ื ืžื”ืฉื•ืจื” ื”ืจืืฉื•ื ื” ืžืจื—ื‘ื™ ื”ืขื•ืœื. ืœื—ืฅ ืคืขืžื™ื™ื ืขืœ ื”ื›ืชื•ื‘ื™ื•ืช ื‘ืื ื’ืœื™ืช ื”ืžื•ืฆื’ื•ืช ื‘ื›ืœ ื“ืฃ ื•ื™ื“ืื• ื›ื“ื™ ืœื”ืคืขื™ืœ ืืช ื”ืกืจื˜ื•ืŸ ืžืฉื. ื”ื›ืชื•ื‘ื™ื•ืช ื’ื•ืœืœื•ืช ื‘ืกื ื›ืจื•ืŸ ืขื ื”ืคืขืœืช ื”ื•ื•ื™ื“ืื•. ืื ื™ืฉ ืœืš ื”ืขืจื•ืช ืื• ื‘ืงืฉื•ืช, ืื ื ืฆื•ืจ ืื™ืชื ื• ืงืฉืจ ื‘ืืžืฆืขื•ืช ื˜ื•ืคืก ื™ืฆื™ืจืช ืงืฉืจ ื–ื”.

https://forms.gle/WvT1wiN1qDtmnspy7