1
00:00:02,600 --> 00:00:04,610
Everyone and welcome back to this class

2
00:00:08,330 --> 00:00:13,630
this is a short lecture I like to give in each of my courses on how to succeed in this course.

3
00:00:13,700 --> 00:00:18,560
This is very important to talk about because you're learning a difficult technical subject.

4
00:00:18,560 --> 00:00:19,760
It's easy to get stuck.

5
00:00:19,880 --> 00:00:23,340
Or even worse give up because you're just not getting things.

6
00:00:23,450 --> 00:00:27,240
Maybe there are too many gaps in your knowledge so you can't connect the dots.

7
00:00:27,260 --> 00:00:30,100
Maybe some assumption you've made is incorrect.

8
00:00:30,500 --> 00:00:33,500
And keep in mind there is a lot of material in this course.

9
00:00:33,500 --> 00:00:38,780
It can be overwhelming if you're new to this field of study and you're not familiar with the conventions

10
00:00:38,810 --> 00:00:41,510
and the typical patterns we use.

11
00:00:41,650 --> 00:00:47,110
Now if you've already seen this lecture in the past you're more than welcome to skip it if you remember

12
00:00:47,110 --> 00:00:50,150
what's in it and you're already using these guidelines.

13
00:00:55,120 --> 00:00:57,450
The first guideline is this.

14
00:00:57,460 --> 00:00:59,960
Remember that I want you to succeed.

15
00:00:59,980 --> 00:01:03,760
In fact that's why I'm giving you these guidelines in the first place.

16
00:01:03,760 --> 00:01:09,870
So if at any point when you watching these lectures and you become confused just ask on the Q&A.

17
00:01:09,910 --> 00:01:16,720
Also known as the discussion forum Typically I respond within hours sometimes even within minutes if

18
00:01:16,720 --> 00:01:20,410
I happen to be on the site and I see a notification.

19
00:01:20,410 --> 00:01:22,320
I answer any and all questions.

20
00:01:22,330 --> 00:01:25,240
So even if you think it's stupid just ask.

21
00:01:25,240 --> 00:01:30,550
Anyway one example I get from time to time is where do I get the code for this course.

22
00:01:30,820 --> 00:01:36,370
And of course my answer is typically Well it's in a lecture called where to get the code for this course.

23
00:01:36,610 --> 00:01:40,830
At the end of the day no one cares if your question was trivial or silly.

24
00:01:40,930 --> 00:01:44,750
If it's something keeping you from progressing in the course I want to answer it.

25
00:01:49,660 --> 00:01:55,270
Now Very rarely I get people saying well I was so confused that I couldn't even think of the right question

26
00:01:55,290 --> 00:02:00,860
ask and this is where you have to take some responsibility for your own learning.

27
00:02:00,970 --> 00:02:06,690
You have to ask yourself what did the instructor assume I know that I didn't actually know.

28
00:02:06,910 --> 00:02:10,979
Maybe I can look into those things and that will help me formulate a question.

29
00:02:11,110 --> 00:02:16,570
Maybe there's some background knowledge I'm missing a lot of people like to have exercises to practice

30
00:02:16,630 --> 00:02:23,240
when they're taking a course the active thinking of the right question to ask is itself an exercise.

31
00:02:23,380 --> 00:02:28,790
It might not be the type of exercise you thought you'd be doing but in many ways this is more profound.

32
00:02:28,810 --> 00:02:34,690
This is an exercise that requires you to think and to change how you think and ultimately that is the

33
00:02:34,690 --> 00:02:36,800
best value you can get out of course.

34
00:02:41,890 --> 00:02:47,710
Speaking of background knowledge this is one of the most important guidelines in this lecture.

35
00:02:47,930 --> 00:02:53,600
You may have noticed that in the course description I've listed some prerequisites or in other words

36
00:02:53,840 --> 00:02:56,320
things you should know before starting this course.

37
00:02:57,030 --> 00:03:00,240
Now you might wonder why do I ask you to know these things.

38
00:03:00,330 --> 00:03:05,760
Why don't I just teach them in the course and while we do review some topics in this course it's not

39
00:03:05,760 --> 00:03:07,080
the focus.

40
00:03:07,080 --> 00:03:12,750
There is such a wide variety of students in this Course students from almost every country in the world.

41
00:03:12,810 --> 00:03:15,700
Students of all ages students of all backgrounds.

42
00:03:16,020 --> 00:03:17,220
What does this mean.

43
00:03:17,990 --> 00:03:22,530
That means let's review for one person is going to be totally new for another.

44
00:03:22,550 --> 00:03:25,280
Some people are going to tell me they don't know calculus.

45
00:03:25,280 --> 00:03:29,390
Some people are going to be very far behind with their Python programming skills.

46
00:03:32,520 --> 00:03:38,370
But if we start teaching Python programming skills other people are going to say hey why are we doing

47
00:03:38,370 --> 00:03:41,590
Python isn't the topic of this course deep learning.

48
00:03:41,730 --> 00:03:44,370
And I tend to agree that we should stay on topic.

49
00:03:44,700 --> 00:03:51,060
So how can we reconcile this well it doesn't make sense for me to give you an entire computer science

50
00:03:51,060 --> 00:03:56,530
education in this one course because a lot of that would be irrelevant for a lot of people.

51
00:03:56,640 --> 00:04:02,180
The only logical thing to do is for all of us to meet at a common meeting point.

52
00:04:02,310 --> 00:04:03,740
How is that point defined.

53
00:04:04,020 --> 00:04:06,410
Well it's defined by the course prerequisites.

54
00:04:06,660 --> 00:04:12,900
In fact they are so important that in certain instances I've listed the cause prerequisites twice just

55
00:04:12,900 --> 00:04:14,770
in case you missed it the first time.

56
00:04:14,910 --> 00:04:17,240
And I'm also reminding you now for good measure.

57
00:04:22,010 --> 00:04:27,290
Now one pitfall is that people sometimes assume they know things that they don't really know.

58
00:04:27,290 --> 00:04:33,080
So if you took calculus 20 years ago and you got a C and you skipped class and the times that you didn't

59
00:04:33,080 --> 00:04:37,580
show up for class you were sleeping well probably you don't know that much calculus.

60
00:04:37,880 --> 00:04:40,100
But remember I want you to succeed.

61
00:04:40,310 --> 00:04:43,130
I want you to be able to learn this material.

62
00:04:43,130 --> 00:04:48,560
I can point you to resources where you can pick up this missing background knowledge but the key is

63
00:04:48,560 --> 00:04:50,450
you have to ask.

64
00:04:50,610 --> 00:04:55,770
In some cases there are certain places where I'm not allowed to post certain links so we have to be

65
00:04:55,770 --> 00:04:58,570
mindful of the rules of the platform we're using.

66
00:05:03,350 --> 00:05:09,230
Now occasionally people ask me Well why don't you just teach a course for pure beginners Why don't you

67
00:05:09,230 --> 00:05:15,440
teach these courses in such a way that they don't require lots of math and lots of prerequisites While

68
00:05:15,440 --> 00:05:20,210
I don't want to turn this into an easy beginner's type of course because for one that's not what I'm

69
00:05:20,210 --> 00:05:21,770
interested in personally.

70
00:05:21,980 --> 00:05:25,940
And number two don't forget that this is State of the art stuff.

71
00:05:26,090 --> 00:05:31,970
State of the art generally isn't easy and if it were easy that would mean everyone is doing it.

72
00:05:31,970 --> 00:05:36,830
And if a thousand other people can do the same thing as you well what's a potential employer going to

73
00:05:36,830 --> 00:05:44,220
think what are your chances of getting that job when all 1000 of you have the exact same skills.

74
00:05:44,290 --> 00:05:46,710
So we don't want skills that are easy to get.

75
00:05:46,720 --> 00:05:52,030
We want skills that are hard to get skills that puts you at the top of your game skills that not many

76
00:05:52,030 --> 00:05:53,280
people have.

77
00:05:53,290 --> 00:05:58,780
If I'm hiring someone I want the guy who stands out not the guy who says the same thing as everyone

78
00:05:58,780 --> 00:05:59,450
else.

79
00:06:04,070 --> 00:06:07,970
Finally the final guideline for how to succeed in this course.

80
00:06:08,240 --> 00:06:13,800
I mentioned earlier that there is a lot of material so much that it can be hard to keep track of.

81
00:06:13,840 --> 00:06:19,330
In addition to taking your own notes and doing all the derivations yourself how can you be absolutely

82
00:06:19,330 --> 00:06:22,000
sure you're understanding this material.

83
00:06:22,120 --> 00:06:26,200
I would in fact consider this even more important than the derivations.

84
00:06:26,200 --> 00:06:31,940
Not everyone is going to be a pro at math so it's understandable if you want to skip a few steps.

85
00:06:31,990 --> 00:06:37,560
Sometimes it's possible to compartmentalize some concepts or delegate learning them for some other time

86
00:06:38,050 --> 00:06:42,620
but still understanding the high level picture and how it fits in with everything else.

87
00:06:43,190 --> 00:06:46,460
What you cannot skip is the implementation.

88
00:06:46,460 --> 00:06:52,200
Implementing these algorithms in code is the real test for whether or not you understand the material

89
00:06:57,220 --> 00:07:02,380
and this is not about reinventing the wheel or that you shouldn't roll your own whatever because someone

90
00:07:02,380 --> 00:07:04,540
else out there can do it better than you.

91
00:07:04,540 --> 00:07:09,960
That is a software engineering principle not a principle of learning in production.

92
00:07:09,970 --> 00:07:13,190
You don't want to write your own hash map or your own string class.

93
00:07:13,450 --> 00:07:20,410
And yet what do we usually do as an exercise in a typical intro to computer science class where we do

94
00:07:20,410 --> 00:07:21,600
precisely that.

95
00:07:21,670 --> 00:07:26,830
We implemented hash maps and we implemented strings.

96
00:07:26,920 --> 00:07:28,410
And why do we do this.

97
00:07:28,780 --> 00:07:32,800
Because we want to have a better understanding of how these things work.

98
00:07:32,800 --> 00:07:38,590
If you make an assumption that's incorrect while your code is probably just not going to work merely

99
00:07:38,590 --> 00:07:44,830
using a hash map and using a string only gives you a very superficial understanding that's beginner

100
00:07:44,830 --> 00:07:51,090
stuff that's stuff everyone knows that's not stuff that's going to help you stand out from the competition.

101
00:07:51,250 --> 00:07:56,710
And it's true that you'll never use your own homemade hash map of your own home made string in any code

102
00:07:56,710 --> 00:07:57,380
you write.

103
00:07:57,610 --> 00:08:01,600
Unless of course you are a professional that focuses on that sort of thing.

104
00:08:01,900 --> 00:08:07,030
They'll probably be inefficient and they'll probably have bugs but that's OK because you're not doing

105
00:08:07,030 --> 00:08:08,750
it to make it perfect.

106
00:08:08,830 --> 00:08:11,320
You're doing it to learn.

107
00:08:11,340 --> 00:08:16,500
You'll notice that the general pattern that this course follows is that we always discuss theory and

108
00:08:16,500 --> 00:08:18,700
then we implement that theory in code.

109
00:08:18,780 --> 00:08:24,680
So we're always going from theory to code implementing everything that we learned.

110
00:08:24,760 --> 00:08:31,390
If you can try to implement something before watching the coding lecture in the appendix I have a lecture

111
00:08:31,390 --> 00:08:33,409
called How to code by yourself.

112
00:08:33,580 --> 00:08:39,640
That goes much more in-depth into this topic along with multiple strategies for how to approach implementation

113
00:08:39,640 --> 00:08:40,640
exercises.

114
00:08:45,360 --> 00:08:50,900
So to summarize these are the guidelines I think are going to help you succeed in this course.

115
00:08:50,910 --> 00:08:58,320
Number one make generous use of the Q&A even when you can't think of the right question ask.

116
00:08:58,390 --> 00:09:02,410
Number two make sure you meet the prerequisites to this course.

117
00:09:02,560 --> 00:09:08,280
If you're not sure what they are or you're not sure how the guideline number one.

118
00:09:08,430 --> 00:09:10,390
Number three try your best.

119
00:09:10,410 --> 00:09:12,340
Implement everything we learn.

120
00:09:12,450 --> 00:09:17,480
This is the true test for whether or not you understand something.

121
00:09:17,540 --> 00:09:20,700
Remember that it's perfectly normal to get stuck once in a while.

122
00:09:21,080 --> 00:09:23,230
I get stuck all the time when I'm learning.

123
00:09:23,300 --> 00:09:25,000
That doesn't mean I'm not smart.

124
00:09:25,250 --> 00:09:28,620
Nor does it mean the book or video I'm learning from is bad.

125
00:09:28,640 --> 00:09:33,860
It means that there is a disconnect between what the author believes I knew and what I actually know

126
00:09:34,550 --> 00:09:41,840
and as a learner I do my best to close that gap a good skill to have is learning how to compartmentalize

127
00:09:41,840 --> 00:09:42,730
concepts.

128
00:09:42,920 --> 00:09:47,810
So here are the things I understand here are the things I don't understand but here are the things I

129
00:09:47,840 --> 00:09:50,170
understand about the things I don't understand.

130
00:09:50,360 --> 00:09:52,340
And these are the holes.

131
00:09:52,340 --> 00:09:56,510
So you know what you're missing and you know where they fit and you can work to fill in those gaps over

132
00:09:56,510 --> 00:09:57,200
time.

133
00:09:58,120 --> 00:10:03,100
One thing I've been doing quite a bit recently is adding review lectures to my courses.

134
00:10:03,400 --> 00:10:08,260
These are meant to teach you everything from scratch since that's going to take you a long time but

135
00:10:08,260 --> 00:10:11,510
they are meant to help you recall certain things you may have forgotten.

136
00:10:11,800 --> 00:10:17,320
So if you have an idea for a review lecture that you'd like to see added to this course please feel

137
00:10:17,320 --> 00:10:19,300
free to make a suggestion using the Q&A.

