Would you like to inspect the original subtitles? These are the user uploaded subtitles that are being translated:
1
00:00:01,440 --> 00:00:02,700
Instructor: We will start with one of the
2
00:00:02,700 --> 00:00:04,890
simplest transformations.
3
00:00:04,890 --> 00:00:06,780
Often we are not interested
4
00:00:06,780 --> 00:00:09,513
in an absolute value, but a relative value.
5
00:00:10,620 --> 00:00:13,980
That's usually the case when working with stock prices.
6
00:00:13,980 --> 00:00:17,040
If you open Google and type Apple stock price,
7
00:00:17,040 --> 00:00:19,860
what you'll get is Apple stock price,
8
00:00:19,860 --> 00:00:21,870
but with red or green numbers,
9
00:00:21,870 --> 00:00:24,513
the relative change in Apple stock price.
10
00:00:25,710 --> 00:00:28,950
This is an example of pre-processing that is so common
11
00:00:28,950 --> 00:00:30,960
we don't consider it as such.
12
00:00:30,960 --> 00:00:33,420
Relative metrics are especially useful
13
00:00:33,420 --> 00:00:36,630
when we have a time series data, like stock prices,
14
00:00:36,630 --> 00:00:38,913
Forex exchange rates, and so on.
15
00:00:41,310 --> 00:00:43,140
Still in the world of finance,
16
00:00:43,140 --> 00:00:45,540
we can further transform these relative changes
17
00:00:45,540 --> 00:00:47,190
into logarithms.
18
00:00:47,190 --> 00:00:49,710
Many statistical and mathematical methods
19
00:00:49,710 --> 00:00:51,180
take advantage of logarithms
20
00:00:51,180 --> 00:00:53,790
as they facilitate faster computation.
21
00:00:53,790 --> 00:00:54,960
In machine learning,
22
00:00:54,960 --> 00:00:57,210
log transformations are not as common
23
00:00:57,210 --> 00:00:59,313
but can increase the speed of learning.
24
00:01:01,050 --> 00:01:02,640
Okay, great.
25
00:01:02,640 --> 00:01:05,940
So this is one type of pre-processing we wanted to give
26
00:01:05,940 --> 00:01:07,170
as an example.
27
00:01:07,170 --> 00:01:09,150
Let's continue to our next lesson,
28
00:01:09,150 --> 00:01:11,760
where we will deal with pre-processing transformations
29
00:01:11,760 --> 00:01:14,910
that are more typical for the world of machine learning.
30
00:01:14,910 --> 00:01:17,253
Stick around, and thanks for watching.
2269
Can't find what you're looking for?
Get subtitles in any language from opensubtitles.com, and translate them here.
Afrikaans
Akan
Albanian
Amharic
Arabic
Armenian
Azerbaijani
Basque
Belarusian
Bemba
Bengali
Bihari
Bosnian
Breton
Bulgarian
Cambodian
Catalan
Cebuano
Cherokee
Chichewa
Chinese (Simplified)
Chinese (Traditional)
Corsican
Croatian
Czech
Danish
Dutch
English
Esperanto
Estonian
Faroese
Finnish
Galician
Georgian
German
Greek
Guarani
Haitian Creole
Hausa
Hawaiian
Hebrew
Hmong
Hungarian
Icelandic
Indonesian
Irish
Italian
Japanese
Kazakh
Kinyarwanda
Kirundi
Kongo
Korean
Krio (Sierra Leone)
Kurdish
Kyrgyz
Laothian
Latin
Latvian
Lithuanian
Luganda
Luo
Luxembourgish
Macedonian
Malagasy
Malay
Maltese
Maori
Mauritian Creole
Moldavian
Mongolian
Myanmar (Burmese)
Montenegrin
Nepali
Norwegian
Pashto
Polish
Portuguese (Brazil)
Portuguese (Portugal)
Quechua
Romanian
Romansh
Russian
Samoan
Scots Gaelic
Serbian
Sesotho
Setswana
Seychellois Creole
Shona
Sindhi
Sinhalese
Slovak
Slovenian
Somali
Spanish
Swedish
Tajik
Thai
Tigrinya
Tonga
Turkish
Turkmen
Ukrainian
Uzbek
Vietnamese
Welsh
Wolof