1
00:00:00,000 --> 00:00:04,578
[MUSIC]

2
00:00:04,578 --> 00:00:08,558
But before we delve into the course
itself, let's just talk about what we're

3
00:00:08,558 --> 00:00:12,680
assuming you have as background in order
to successfully complete this course.

4
00:00:13,730 --> 00:00:16,490
So in terms of math background,
we're assuming that you know

5
00:00:16,490 --> 00:00:20,780
very basic calculus like how to take
the derivative of a single variable.

6
00:00:20,780 --> 00:00:21,940
Function.

7
00:00:21,940 --> 00:00:25,300
But even that we're gonna walk
through fairly slowly, but

8
00:00:25,300 --> 00:00:26,910
it's good if you remember it.

9
00:00:26,910 --> 00:00:30,750
We're also gonna assume that you know
how to do very basic linear algebra

10
00:00:30,750 --> 00:00:36,240
manipulations like how to
multiply to vectors, to matrices,

11
00:00:36,240 --> 00:00:41,470
and also of course what the notion is of
a matrix and a vector, but again, we're

12
00:00:41,470 --> 00:00:45,740
gonna step through these ideas fairly
slowly at the beginning of the course.

13
00:00:45,740 --> 00:00:49,500
In terms of programming experience,
we've tried to make this course

14
00:00:49,500 --> 00:00:53,710
as open as possible to people having
preferences in different languages.

15
00:00:53,710 --> 00:00:56,970
We're gonna, encourage the use of Python.

16
00:00:56,970 --> 00:01:00,090
But this is not actually required.

17
00:01:01,780 --> 00:01:05,340
So all of our programming assignments,
we're gonna provide you with some starter

18
00:01:05,340 --> 00:01:08,170
code and
that starter code will be in Python.

19
00:01:08,170 --> 00:01:12,340
So of course it's helpful if you
are familiar with Python, but

20
00:01:12,340 --> 00:01:15,430
again you're welcome to use
any language you would like.

21
00:01:15,430 --> 00:01:20,130
We're focused on teaching you
the concepts of machine learning

22
00:01:20,130 --> 00:01:23,660
rather than any specific
implementation details.

23
00:01:23,660 --> 00:01:26,620
But, I should mention that if you
did programming assignments for

24
00:01:26,620 --> 00:01:31,470
the first course, you are set for
what will be required in this course.

25
00:01:31,470 --> 00:01:33,370
So in the first course
of this specialization,

26
00:01:33,370 --> 00:01:38,400
we relied on pre-implemented algorithms
like GraphLab Create, but in this course,

27
00:01:38,400 --> 00:01:41,450
we're actually going to teach you all
the all the algorithmic details and

28
00:01:41,450 --> 00:01:46,230
how to implement these algorithms so
that you can code these up yourself.

29
00:01:46,230 --> 00:01:51,200
So in particular, in this course,
we're suggesting that you use SFrames,

30
00:01:51,200 --> 00:01:56,900
which from the first course you remember
is an open source library that allows for

31
00:01:56,900 --> 00:02:00,930
really scalable and efficient data
manipulation, but you're welcome to use

32
00:02:00,930 --> 00:02:06,040
any data structure that you would like or
library such as pandas.

33
00:02:06,040 --> 00:02:08,480
And for our assignments.

34
00:02:08,480 --> 00:02:11,520
The structure of the assignments are going
to start with exploring high level

35
00:02:11,520 --> 00:02:13,540
concepts in the first part and

36
00:02:13,540 --> 00:02:16,970
then delving into that implementation
details of each of the algorithms.

37
00:02:16,970 --> 00:02:20,340
So for the first part, we're going to
encourage the use of pre-implemented

38
00:02:20,340 --> 00:02:24,210
algorithms, so that you can test these
high level concepts without getting bogged

39
00:02:24,210 --> 00:02:27,490
down in potential bugs in
your actual implementation.

40
00:02:27,490 --> 00:02:30,750
And then in the second part,
once you've explored those concepts,

41
00:02:30,750 --> 00:02:34,910
then we're gonna have you actually
implement all the algorithms from scratch

42
00:02:34,910 --> 00:02:38,991
without relying on these
pre-implemented methods.

43
00:02:40,180 --> 00:02:44,000
If you're using Python,
you will be using the Numpy library for

44
00:02:44,000 --> 00:02:45,990
manipulating matrices and vectors.

45
00:02:47,090 --> 00:02:49,320
Okay, so
the net result is that in this course,

46
00:02:49,320 --> 00:02:53,510
you're really gonna get your hands
dirty in implementing all the methods.

47
00:02:53,510 --> 00:02:57,150
Related to regression that you saw in
the first foundational course this

48
00:02:57,150 --> 00:03:00,000
specialization as well as a bunch
of new methods that we're

49
00:03:00,000 --> 00:03:02,310
gonna explore in this course.

50
00:03:02,310 --> 00:03:03,030
So finally,

51
00:03:03,030 --> 00:03:06,840
let's discuss what computing resources
you guys need and there are two options.

52
00:03:06,840 --> 00:03:12,850
Either, you have your own computer and it
can actually be a fairly basic computer.

53
00:03:12,850 --> 00:03:17,500
But if you are gonna use SFrames,
you are gonna need a 64-bit machine.

54
00:03:17,500 --> 00:03:21,510
You'll also need to have access to
the internet, of course, to watch

55
00:03:21,510 --> 00:03:26,540
these wonderful videos, as well as to
implement your programming assignments.

56
00:03:26,540 --> 00:03:30,890
And you'll need the ability to install and
run Python.

57
00:03:32,140 --> 00:03:35,050
And any libraries we're using
associated with that and

58
00:03:35,050 --> 00:03:39,720
to store a few gigabytes of data, but
the alternative, especially if you

59
00:03:39,720 --> 00:03:44,960
don't have a 64-bit machine, is we're
providing a set of machines in the cloud

60
00:03:44,960 --> 00:03:50,350
that are pre-configured with
everything you'll need for this course.

61
00:03:50,350 --> 00:03:54,430
So all you'll need is internet access
to access those machines in the cloud.

62
00:03:55,850 --> 00:03:59,330
So now that you guys are psyched
about this course, let's get started.

63
00:03:59,330 --> 00:04:03,409
[MUSIC]