Can robots be creative? - Gil Weinberg

496,200 views ใƒป 2015-03-19

TED-Ed


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

ืชืจื’ื•ื: Ido Dekkers ืขืจื™ื›ื”: Tal Dekkers
00:10
How does this music make you feel?
0
10727
2305
ืื™ืš ื”ืžื•ื–ื™ืงื” ื”ื–ื• ื’ื•ืจืžืช ืœื›ื ืœื”ืจื’ื™ืฉ?
00:13
Do you find it beautiful?
1
13032
1669
ื”ืื ืืชื ืžื•ืฆืื™ื ืื•ืชื” ื™ืคื™ืคื™ื™ื”?
00:14
Is it creative?
2
14701
1636
ื”ืื ื”ื™ื ื™ืฆื™ืจืชื™ืช?
00:16
Now, would you change your answers
3
16337
1705
ืขื›ืฉื™ื•, ื”ื™ื™ืชื ืžืฉื ื™ื ืืช ื”ืชืฉื•ื‘ื”
00:18
if you learned the composer was this robot?
4
18042
3480
ืื ื”ื™ื™ืชื ืœืžื“ื™ื ืฉื”ืžืœื—ื™ืŸ ื”ื•ื ื”ืจื•ื‘ื•ื˜ ื”ื–ื”?
00:21
Believe it or not,
5
21522
1979
ืชืืžื™ื ื• ืื• ืœื,
00:23
people have been grappling with the question of artificial creativity,
6
23501
3317
ืื ืฉื™ื ื”ืชืžื•ื“ื“ื• ืขื ื”ืฉืืœื” ืฉืœ ื™ืฆื™ืจืชื™ื•ืช ืžืœืื›ื•ืชื™ืช,
00:26
alongside the question of artifcial intelligence,
7
26818
3007
ื™ื—ื“ ืขื ื”ืฉืืœื” ืฉืœ ื‘ื™ื ื” ืžืœืื›ื•ืชื™ืช,
00:29
for over 170 years.
8
29825
3007
ื‘ืžืฉืš ื™ื•ืชืจ ืž 170 ืฉื ื”.
00:32
In 1843, Lady Ada Lovelace,
9
32832
3008
ื‘ 1843, ืœื™ื™ื“ื™ ืขื“ื” ืœืื‘ืœื™ื™ืก,
00:35
an English mathematician considered the world's first computer programmer,
10
35840
4309
ืžืชืžื˜ื™ืงืื™ืช ืื ื’ืœื™ื” ืฉื ื—ืฉื‘ื” ืœืžืชื›ื ืชืช ื”ืžื—ืฉื‘ื™ื ื”ืจืืฉื•ื ื” ื‘ืขื•ืœื,
00:40
wrote that a machine could not have human-like intelligence
11
40149
3428
ื›ืชื‘ื” ืฉืœืžื›ื•ื ื” ืœื ืชื•ื›ืœ ืœื”ื™ื•ืช ื‘ื™ื ื” ื“ืžื•ื™ื™ืช ืื“ื
00:43
as long as it only did what humans intentionally programmed it to do.
12
43577
5430
ื›ืœ ืขื•ื“ ื”ื™ื ืขื•ืฉื” ืจืง ืžื” ืฉื‘ื ื™ ืื“ื ืชื™ื›ื ืชื• ืื•ืชื” ื‘ืžื›ื•ื•ืŸ ืœืขืฉื•ืช.
00:49
According to Lovelace,
13
49007
1702
ืœืคื™ ืœืื‘ืœื™ื™ืก,
00:50
a machine must be able to create original ideas
14
50709
2985
ืžื›ื•ื ื” ื—ื™ื™ื‘ืช ืœื”ื™ื•ืช ืžืกื•ื’ืœืช ืœื™ืฆื•ืจ ืจืขื™ื•ื ื•ืช ืžืงื•ืจื™ื™ื
00:53
if it is to be considered intelligent.
15
53694
3698
ื‘ื›ื“ื™ ืœื”ื™ื—ืฉื‘ ื›ืื™ื ื˜ื™ืœื™ื’ื ื˜ื™ืช.
00:57
The Lovelace Test, formalized in 2001, proposes a way of scrutinizing this idea.
16
57392
6422
ืžื‘ื—ืŸ ืœืื‘ืœื™ื™ืก, ืฉื”ืคืš ืœืจืฉืžื™ ื‘ 2001, ืžืฆื™ืข ื“ืจืš ืœื‘ื—ื•ืŸ ืืช ื”ืจืขื™ื•ืŸ.
01:03
A machine can pass this test if it can produce an outcome
17
63814
3442
ืžื›ื•ื ื” ื™ื›ื•ืœื” ืœืขื‘ื•ืจ ืืช ื”ืžื‘ื—ืŸ ืื ื”ื™ื ื™ื›ื•ืœื” ืœื™ืฆื•ืจ ืชื•ืฆืื”
01:07
that its designers cannot explain based on their original code.
18
67256
5004
ืฉื”ืžืชื›ื ืช ืฉืœื” ืœื ื™ื›ื•ืœ ืœื”ืกื‘ื™ืจ ื‘ื”ืชื‘ืกืก ืขืœ ื”ืงื•ื“ ื”ืžืงื•ืจื™.
01:12
The Lovelace Test is, by design, more of a thought experiment
19
72260
3349
ืžื‘ื—ืŸ ืœืื‘ืœื™ื™ืก ื”ื•ื, ื‘ืชื›ื ื•ื ื•, ื™ื•ืชืจ ื ื™ืกื•ื™ ืžื—ืฉื‘ืชื™
01:15
than an objective scientific test.
20
75609
2411
ืžืžื‘ื—ืŸ ืžื“ืขื™ ืื•ื‘ื™ื™ืงื˜ื™ื‘ื™.
01:18
But it's a place to start.
21
78020
2019
ืื‘ืœ ื–ื” ืžืงื•ื ืœื”ืชื—ื™ืœ.
01:20
At first glance,
22
80039
1194
ื‘ืžื‘ื˜ ืจืืฉื•ืŸ,
01:21
the idea of a machine creating high quality, original music in this way
23
81233
3920
ื”ืจืขื™ื•ืŸ ืฉืœ ืžื›ื•ื ื” ืฉื™ื•ืฆืจืช ืžื•ื–ื™ืงื” ืื™ื›ื•ืชื™ืช ื•ืžืงื•ืจื™ืช ื‘ื“ืจืš ื–ื•
01:25
might seem impossible.
24
85153
2155
ืื•ืœื™ ืชืจืื” ื‘ืœืชื™ ืืคืฉืจื™ืช.
01:27
We could come up with an extremely complex algorithm
25
87308
2894
ื ื•ื›ืœ ืœื”ืขืœื•ืช ืืœื’ื•ืจืชืžื™ื ืžืกื•ื‘ื›ื™ื ืœื”ืคืœื™ื
01:30
using random number generators, chaotic functions, and fuzzy logic
26
90202
4141
ื‘ืฉื™ืžื•ืฉ ื‘ืžื™ื™ืฆืจื™ ืžืกืคืจื™ื ืจื ื“ื•ืžืœื™ื™ื, ืคื•ื ืงืฆื™ื•ืช ื›ืื•ื˜ื™ื•ืช ื•ืœื•ื’ื™ืงื” ืขืžื•ืžื”
01:34
to generate a sequence of musical notes
27
94343
2459
ื›ื“ื™ ืœื™ืฆื•ืจ ืกื“ืจื” ืฉืœ ืชื•ื™ื ืžื•ื–ื™ืงืœื™ื™ื
01:36
in a way that would be impossible to track.
28
96802
2674
ื‘ื“ืจืš ืฉืชื”ื™ื” ื‘ืœืชื™ ืืคืฉืจื™ืช ืœืขืงื•ื‘ ืื—ืจื™ื”.
01:39
But although this would yield countless original melodies never heard before,
29
99476
3795
ืื‘ืœ ืœืžืจื•ืช ืฉื–ื” ื™ืคื™ืง ืžืœื•ื“ื™ื•ืช ืžืงื•ืจื™ื•ืช ืจื‘ื•ืช ืžืกืคื•ืจ ืฉืžืขื•ืœื ืœื ื ืฉืžืขื• ืงื•ื“ื ืœื›ืŸ,
01:43
only a tiny fraction of them would be worth listening to.
30
103271
3943
ืจืง ื—ืœืงื™ืง ื–ืขื™ืจ ืžื”ื ื™ื”ื™ื” ืฉื•ื•ื” ืฉืžื™ืขื”.
01:47
With the computer having no way to distinguish
31
107214
2337
ื›ืฉืœืžื—ืฉื‘ ืื™ืŸ ื“ืจืš ืœื”ื‘ื—ื™ืŸ
01:49
between those which we would consider beautiful
32
109551
2423
ื‘ื™ืŸ ืืœื” ืฉื™ื—ืฉื‘ื• ื™ืคื™ืคื™ื™ื•ืช
01:51
and those which we won't.
33
111974
2637
ื•ืืœื” ืฉืœื.
01:54
But what if we took a step back
34
114611
1637
ืื‘ืœ ืžื” ืื ื”ื™ื™ื ื• ืœื•ืงื—ื™ื ืฆืขื“ ืื—ื•ืจื”
01:56
and tried to model a natural process that allows creativity to form?
35
116248
4973
ื•ืžื ืกื™ื ืœืžื“ืœ ืชื”ืœื™ืš ื˜ื‘ืขื™ ืฉืžืืคืฉืจ ืœื™ืฆื™ืจืชื™ื•ืช ืœื”ื•ื•ืฆืจ?
02:01
We happen to know of at least one such process
36
121221
2252
ืื ื—ื ื• ื™ื•ื“ืขื™ื ืขืœ ืœืคื—ื•ืช ืชื”ืœื™ืš ืื—ื“ ื›ื–ื”
02:03
that has lead to original, valuable, and even beautiful outcomes:
37
123473
4522
ืฉื”ื•ื‘ื™ืœ ืœืชื•ืฆืื•ืช ืžืงื•ืจื™ื•ืช, ื‘ืขืœื•ืช ืขืจืš, ื•ืืคื™ืœื• ื™ืคื™ืคื™ื•ืช:
02:07
the process of evolution.
38
127995
2788
ื”ืชื”ืœื™ืš ืฉืœ ืื‘ื•ืœื•ืฆื™ื”.
02:10
And evolutionary algorithms,
39
130783
2198
ื•ืืœื’ื•ืจื™ืชืžื™ื ืื‘ื•ืœื•ืฆื™ื•ื ื™ื,
02:12
or genetic algorithms that mimic biological evolution,
40
132981
3259
ืื• ืืœื’ื•ืจื™ืชืžื™ื ื’ื ื˜ื™ื ืฉืžื—ืงื™ื ืื‘ื•ืœื•ืฆื™ื” ื‘ื™ื•ืœื•ื’ื™ืช,
02:16
are one promising approach
41
136240
2303
ื”ื ื’ื™ืฉื” ืื—ืช ืžื‘ื˜ื™ื—ื”
02:18
to making machines generate original and valuable artistic outcomes.
42
138543
6020
ืœื’ืจื•ื ืœืžื›ื•ื ื•ืช ืœื™ื™ืฆืจ ืชื•ืฆืื•ืช ืžืงื•ืจื™ื•ืช ื•ื‘ืขืœื•ืช ืขืจืš ืื•ืžื ื•ืชื™.
02:24
So how can evolution make a machine musically creative?
43
144563
2991
ืื– ืื™ืš ื”ืื‘ื•ืœื•ืฆื™ื” ื™ื›ื•ืœื” ืœื™ืฆื•ืจ ืžื›ื•ื ื” ื™ืฆื™ืจืชื™ืช ืžื•ื–ื™ืงืœื™ืช?
02:27
Well, instead of organisms,
44
147554
2111
ื•ื‘ื›ืŸ, ื‘ืžืงื•ื ืื•ืจื’ื ื™ื–ืžื™ื,
02:29
we can start with an initial population of musical phrases,
45
149665
11713
ืื ื—ื ื• ื™ื›ื•ืœื™ื ืœื”ืชื—ื™ืœ ืขื ืื•ื›ืœื•ืกื™ื” ื”ืชื—ืœืชื™ืช ืฉืœ ืžื•ื ื—ื™ื ืžื•ื–ื™ืงืœื™ื™ื,
02:41
and a basic algorithm
46
161378
1463
ื•ืืœื’ื•ืจื™ืชื ื‘ืกื™ืกื™
02:42
that mimics reproduction and random mutations
47
162841
2924
ืฉืžื—ืงื” ื™ืฆื™ืจื” ื•ืžื•ื˜ืฆื™ื•ืช ืืงืจืื™ื•ืช
02:45
by switching some parts,
48
165765
2412
ืขืœ ื™ื“ื™ ืฉื™ื ื•ื™ ื›ืžื” ื—ืœืงื™ื,
02:48
combining others,
49
168177
1762
ืฉื™ืœื•ื‘ ืื—ืจื™ื,
02:49
and replacing random notes.
50
169939
2414
ื•ื”ื—ืœืคืช ืชื•ื™ื ืืงืจืื™ื™ื.
02:52
Now that we have a new generation of phrases,
51
172353
2698
ืขื›ืฉื™ื• ืฉื™ืฉ ืœื ื• ื“ื•ืจ ื—ื“ืฉ ืฉืœ ืžื•ื ื—ื™ื,
02:55
we can apply selection using an operation called a fitness function.
52
175051
4954
ืื ื—ื ื• ื™ื›ื•ืœื™ื ืœื™ื™ืฉื ื‘ื—ื™ืจื” ื‘ืฉื™ืžื•ืฉ ื‘ืชื”ืœื™ืš ืฉื ืงืจื ืคื•ื ืงืฆื™ืช ื›ื•ืฉืจ.
03:00
Just as biological fitness is determined by external environmental pressures,
53
180005
4302
ืžืžืฉ ื›ืžื• ืฉื›ื•ืฉืจ ื‘ื™ื•ืœื•ื’ื™ ื ืงื‘ืข ืขืœ ื™ื“ื™ ืœื—ืฅ ืžืกื‘ื™ื‘ื•ืช ื—ื™ืฆื•ื ื™ื•ืช,
03:04
our fitness function can be determined by an external melody
54
184307
4157
ืคื•ื ืงืฆื™ื•ืช ื”ื›ื•ืฉืจ ืฉืœื ื• ื™ื›ื•ืœื•ืช ืœื”ืงื‘ืข ืขืœ ื™ื“ื™ ืžืœื•ื“ื™ื” ื—ื™ืฆื•ื ื™ืช
03:08
chosen by human musicians, or music fans,
55
188464
2846
ืฉื ื‘ื—ืจื” ืขืœ ื™ื“ื™ ืžื•ื–ื™ืงืื™ื ืื ื•ืฉื™ื™ื, ืื• ื—ื•ื‘ื‘ื™ ืžื•ื–ื™ืงื”,
03:11
to represent the ultimate beautiful melody.
56
191310
8805
ื›ื“ื™ ืœื™ื™ืฆื’ ืืช ื”ืžืœื•ื“ื™ื” ื”ื™ืคื” ื”ืื•ืœื˜ื™ืžื˜ื™ื‘ื™ืช.
03:20
The algorithm can then compare between our musical phrases
57
200115
3186
ื”ืืœื’ื•ืจื™ืชื ื™ื›ื•ืœ ืื– ืœื”ืฉื•ื•ืช ื‘ื™ืŸ ื”ืžื•ื ื—ื™ื ื”ืžื•ื–ื™ืงืœื™ื™ื ืฉืœื ื•
03:23
and that beautiful melody,
58
203301
1797
ื•ื”ืžืœื•ื“ื™ื” ื”ื™ืคื” ื”ื–ื•,
03:25
and select only the phrases that are most similar to it.
59
205098
3853
ื•ืœื‘ื—ื•ืจ ืจืง ืžื•ื ื—ื™ื ืฉื”ื›ื™ ื“ื•ืžื™ื ืœื”.
03:28
Once the least similar sequences are weeded out,
60
208951
3018
ื‘ืจื’ืข ืฉื”ื—ืœืงื™ื ื”ื›ื™ ืคื—ื•ืช ื“ื•ืžื™ื ืžื•ืฆืื™ื,
03:31
the algorithm can reapply mutation and recombination to what's left,
61
211969
4529
ื”ืืœื’ื•ืจื™ืชื ื™ื›ื•ืœ ืœื”ืคืขื™ืœ ืฉื•ื‘ ืืช ื”ืžื•ื˜ืฆื™ื” ื•ื—ื™ื‘ื•ืจ ืžื—ื“ืฉ ืœืžื” ืฉื ืฉืืจ,
03:36
select the most similar, or fitted ones, again from the new generation,
62
216498
4304
ืœื‘ื—ื•ืจ ืืช ื”ื›ื™ ื“ื•ืžื”, ืื• ื”ื›ื™ ืžืชืื™ื, ืฉื•ื‘ ืžื”ื“ื•ืจ ื”ื—ื“ืฉ,
03:40
and repeat for many generations.
63
220802
7610
ื•ืœื—ื–ื•ืจ ื‘ื”ืจื‘ื” ื“ื•ืจื•ืช.
03:48
The process that got us there has so much randomness and complexity built in
64
228412
4316
ืœืชื”ืœื™ืš ืฉื”ื‘ื™ื ืื•ืชื ื• ืœืฉื ื™ืฉ ื›ืœ ื›ืš ื”ืจื‘ื” ืืงืจืื™ื•ืช ื•ืžื•ืจื›ื‘ื•ืช ืฉื‘ื ื•ื™ื™ื ื‘ืคื ื™ื
03:52
that the result might pass the Lovelace Test.
65
232728
3570
ืฉื”ืชื•ืฆืื” ืื•ืœื™ ืชืขื‘ื•ืจ ืืช ืžื‘ื—ืŸ ืœืื‘ืœื™ื™ืก.
03:56
More importantly, thanks to the presence of human aesthetic in the process,
66
236298
3948
ื•ื™ื•ืชืจ ื—ืฉื•ื‘, ืชื•ื“ื•ืช ืœื ื•ื›ื—ื•ืช ืฉืœ ืืกื˜ืชื™ืงื” ืื ื•ืฉื™ืช ื‘ืชื”ืœื™ืš,
04:00
we'll theoretically generate melodies we would consider beautiful.
67
240246
9081
ืื ื—ื ื• ื ื™ื™ืฆืจ ืชืื•ืจื˜ื™ืช ืžืœื•ื“ื™ื•ืช ืฉื ื•ื›ืœ ืœื”ื—ืฉื™ื‘ ื™ืคื•ืช.
04:09
But does this satisfy our intuition for what is truly creative?
68
249327
4240
ืื‘ืœ ื”ืื ื–ื” ืžืกืคืง ืืช ื”ืื™ื ื˜ื•ืื™ืฆื™ื” ืฉืœื ื• ืœืžื” ืฉื‘ืืžืช ื™ืฆื™ืจืชื™?
04:13
Is it enough to make something original and beautiful,
69
253567
2544
ื”ืื ื–ื” ืžืกืคื™ืง ื›ื“ื™ ืœื™ืฆื•ืจ ืžืฉื”ื• ืžืงื•ืจื™ ื•ื™ืคื”,
04:16
or does creativity require intention and awareness of what is being created?
70
256111
6286
ืื• ื”ืื ื™ืฆื™ืจืชื™ื•ืช ื“ื•ืจืฉืช ื›ื•ื•ื ื” ื•ืžื•ื“ืขื•ืช ืœืžื” ืฉื ื•ืฆืจ?
04:22
Perhaps the creativity in this case is really coming from the programmers,
71
262397
3796
ืื•ืœื™ ื”ื™ืฆื™ืจืชื™ื•ืช ื‘ืžืงืจื” ื”ื–ื” ื‘ืืžืช ืžื’ื™ืขื” ืžื”ืžืชื›ื ืชื™ื,
04:26
even if they don't understand the process.
72
266193
2825
ืืคื™ืœื• ืื ื”ื ืœื ืžื‘ื™ื ื™ื ืืช ื”ืชื”ืœื™ืš.
04:29
What is human creativity, anyways?
73
269018
2186
ืžื” ื”ื™ื ื”ื™ืฆื™ืจืชื™ื•ืช ื”ืื ื•ืฉื™ืช, ื‘ื›ืœ ืื•ืคืŸ?
04:31
Is it something more than a system of interconnected neurons
74
271204
2835
ื”ืื ื”ื™ื ืžืฉื”ื• ื™ื•ืชืจ ืžืžืขืจื›ืช ืฉืœ ื ื™ื•ืจื•ื ื™ื ืžื—ื•ื‘ืจื™ื
04:34
developed by biological algorithmic processes
75
274039
3143
ืฉืคื•ืชื—ื” ืขืœ ื™ื“ื™ ืชื”ืœื™ื›ื™ื ืืœื’ื•ืจื™ืชืžื™ื™ื ื‘ื™ื•ืœื•ื’ื™ื™ื
04:37
and the random experiences that shape our lives?
76
277182
3433
ื•ื”ื—ื•ื•ื™ื” ื”ืืงืจืื™ืช ืฉืžืขืฆื‘ืช ืืช ื—ื™ื™ื ื•?
04:40
Order and chaos, machine and human.
77
280615
3537
ืกื“ืจ ื•ื›ืื•ืก, ืžื›ื•ื ื” ื•ื‘ื ื™ ืื ื•ืฉ.
04:44
These are the dynamos at the heart of machine creativity initiatives
78
284152
4116
ืืœื” ื”ืžื ื•ืขื™ื ื‘ืœื‘ ื™ื•ื–ืžืช ื”ื™ืฆื™ืจืชื™ื•ืช ืฉืœ ื”ืžื›ื•ื ื•ืช
04:48
that are currently making music, sculptures, paintings, poetry and more.
79
288268
6002
ืฉื›ืจื’ืข ื™ื•ืฆืจื™ื ืžื•ื–ื™ืงื”, ืคืกืœื™ื, ืฆื™ื•ืจื™ื, ืฉื™ืจื” ื•ืขื•ื“.
04:54
The jury may still be out
80
294270
1477
ื”ืžื•ืฉื‘ืขื™ื ืื•ืœื™ ืขื“ื™ื™ืŸ ืœื ื”ื—ืœื™ื˜ื•
04:55
as to whether it's fair to call these acts of creation creative.
81
295747
4304
ืื ื–ื” ืคื™ื™ืจ ืœืงืจื•ื ืœืคืขื•ืœื•ืช ื”ื™ืฆื™ืจื” ื”ืืœื• ื™ืฆื™ืจืชื™ื•ืช.
05:00
But if a piece of art can make you weep,
82
300051
2381
ืื‘ืœ ืื ืคื™ืกื” ืฉืœ ืืžื ื•ืช ื™ื›ื•ืœื” ืœื’ืจื•ื ืœื›ื ืœื”ืชื™ื™ืคื—,
05:02
or blow your mind,
83
302432
1541
ืื• ืœืคืชื•ื— ืœื›ื ืืช ื”ืจืืฉ,
05:03
or send shivers down your spine,
84
303973
2161
ืื• ืœืฉืœื•ื— ืฆืžืจืžื•ืจื•ืช ื‘ืžื•ืจื“ ืขืžื•ื“ ื”ืฉื“ืจื” ืฉืœื›ื,
05:06
does it really matter who or what created it?
85
306134
3452
ื”ืื ื–ื” ื‘ืืžืช ืžืฉื ื” ืžื™ ืื• ืžื” ื™ืฆืจ ืื•ืชื”?
ื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