1
00:00:08,450 --> 00:00:11,160
Hi, I'm Chris Brooks.
I'm faculty here at

2
00:00:11,160 --> 00:00:13,950
the School of Information at
the University of Michigan.

3
00:00:13,950 --> 00:00:15,930
I teach in our data
science courses

4
00:00:15,930 --> 00:00:17,985
here and I use Python heavily,

5
00:00:17,985 --> 00:00:19,920
and I work daily
in Python and use

6
00:00:19,920 --> 00:00:21,360
this development environment

7
00:00:21,360 --> 00:00:22,950
called the Jupyter Notebooks.

8
00:00:22,950 --> 00:00:24,855
I'm pleased that I'll be able to

9
00:00:24,855 --> 00:00:27,120
share that with you
through this course.

10
00:00:27,120 --> 00:00:29,190
The Jupyter Notebooks
is a great piece of

11
00:00:29,190 --> 00:00:31,830
technology that allows
you to use the web

12
00:00:31,830 --> 00:00:33,525
essentially to write real-world

13
00:00:33,525 --> 00:00:35,505
Python programs that leverage

14
00:00:35,505 --> 00:00:37,520
really impressive APIs

15
00:00:37,520 --> 00:00:40,790
including optical
character recognition,

16
00:00:40,790 --> 00:00:44,245
and detecting faces,
and so forth.

17
00:00:44,245 --> 00:00:47,220
In my work here, I run
a research lab called

18
00:00:47,220 --> 00:00:49,980
the educational technology
collective or etc.

19
00:00:49,980 --> 00:00:51,305
We do research in

20
00:00:51,305 --> 00:00:53,780
educational technology
and learning analytics.

21
00:00:53,780 --> 00:00:55,860
I'm really interested
in how students,

22
00:00:55,860 --> 00:00:58,290
like yourself, interact
with technology,

23
00:00:58,290 --> 00:01:01,335
like the Coursera platform,
including the contents,

24
00:01:01,335 --> 00:01:02,790
so videos like these,

25
00:01:02,790 --> 00:01:05,375
and your peers on
the discussion forums.

26
00:01:05,375 --> 00:01:07,430
So my research is
really focused on

27
00:01:07,430 --> 00:01:09,260
building things like
predictive models of

28
00:01:09,260 --> 00:01:12,560
student success and studying
how you interact in

29
00:01:12,560 --> 00:01:18,195
these different avenues to
exceed learning expectations.

30
00:01:18,195 --> 00:01:21,560
In this course, we're going
to be more project based,

31
00:01:21,560 --> 00:01:22,715
and it's a little different

32
00:01:22,715 --> 00:01:24,805
focused in the previous courses.

33
00:01:24,805 --> 00:01:27,920
So in the first four courses
in this specialization,

34
00:01:27,920 --> 00:01:30,755
you learn the
fundamentals of Python.

35
00:01:30,755 --> 00:01:32,705
Now we want you to practice

36
00:01:32,705 --> 00:01:35,885
those fundamentals to
try and solve a project.

37
00:01:35,885 --> 00:01:38,330
We're going to introduce
to you new libraries.

38
00:01:38,330 --> 00:01:40,220
Now, the goal here
is not actually to

39
00:01:40,220 --> 00:01:42,710
learn those libraries in detail,

40
00:01:42,710 --> 00:01:44,810
but to learn enough
about those libraries

41
00:01:44,810 --> 00:01:47,445
and moreover to have
this meta-learning,

42
00:01:47,445 --> 00:01:49,160
to learn how to approach

43
00:01:49,160 --> 00:01:51,500
a new library so
that you can start

44
00:01:51,500 --> 00:01:53,510
using your skills in the while

45
00:01:53,510 --> 00:01:56,360
to solve the project so you
might be interested in.

46
00:01:56,360 --> 00:01:58,310
Those libraries are
going to include

47
00:01:58,310 --> 00:02:00,350
image recognition
libraries, so pillow,

48
00:02:00,350 --> 00:02:03,050
and image manipulation,
Tesseract,

49
00:02:03,050 --> 00:02:05,840
which is an optical character
recognition library.

50
00:02:05,840 --> 00:02:09,110
So how we take
pictures of books and

51
00:02:09,110 --> 00:02:10,610
take the texts out of them

52
00:02:10,610 --> 00:02:12,880
and turn into something
we can process.

53
00:02:12,880 --> 00:02:16,980
Cracking, which is
a layout library for tax,

54
00:02:16,980 --> 00:02:18,530
and you'll get a sense for

55
00:02:18,530 --> 00:02:20,240
the challenges that
come when dealing

56
00:02:20,240 --> 00:02:21,890
with taking images and

57
00:02:21,890 --> 00:02:24,010
trying to recognize
characters in them.

58
00:02:24,010 --> 00:02:26,840
Then the last one we'll
introduce is called Open CV,

59
00:02:26,840 --> 00:02:29,210
or CV stands for Computer Vision.

60
00:02:29,210 --> 00:02:32,360
It's used for a lot of things,

61
00:02:32,360 --> 00:02:33,950
but we're going to
focus on using it to

62
00:02:33,950 --> 00:02:36,520
detect faces and pictures,

63
00:02:36,520 --> 00:02:39,095
and your project
will be about that.

64
00:02:39,095 --> 00:02:42,020
So one last thing to
note along with some of

65
00:02:42,020 --> 00:02:44,590
the other faculty here at
the School of Information,

66
00:02:44,590 --> 00:02:47,795
I teach a data science
specialization on Coursera.

67
00:02:47,795 --> 00:02:51,215
We use Python heavily in that
and the Jupyter Notebooks,

68
00:02:51,215 --> 00:02:53,600
and we think that after
you finish the course like

69
00:02:53,600 --> 00:02:56,120
this and come all
the way through it,

70
00:02:56,120 --> 00:02:59,435
you're more than ready to
take that specialization.

71
00:02:59,435 --> 00:03:01,400
So if you want to
continue your learning on

72
00:03:01,400 --> 00:03:04,265
the platform and continue
your learning with us,

73
00:03:04,265 --> 00:03:07,190
please join us in
that specialization.

74
00:03:07,190 --> 00:03:10,150
Let's just dig in
to the class now.