1
00:00:02,510 --> 00:00:04,520
Everyone and welcome back to this class

2
00:00:08,260 --> 00:00:13,560
this is a short lecture I like to give in each of my courses on how to succeed in this course.

3
00:00:13,630 --> 00:00:18,480
This is very important to talk about because you're learning a difficult technical subject.

4
00:00:18,490 --> 00:00:23,040
It's easy to get stuck or even worse give up because you're just not getting things.

5
00:00:23,380 --> 00:00:27,150
Maybe there are too many gaps in your knowledge so you can't connect the dots.

6
00:00:27,190 --> 00:00:30,430
Maybe some assumption you've made is incorrect.

7
00:00:30,430 --> 00:00:33,400
And keep in mind there is a lot of material in this course.

8
00:00:33,400 --> 00:00:38,740
It can be overwhelming if you're new to this field of study and you're not familiar with the conventions

9
00:00:38,740 --> 00:00:41,430
and the typical patterns we use.

10
00:00:41,580 --> 00:00:47,040
Now if you've already seen this lecture in the past you're more than welcome to skip it if you remember

11
00:00:47,040 --> 00:00:50,040
what's in it and you're already using these guidelines.

12
00:00:55,050 --> 00:00:57,360
The first guideline is this.

13
00:00:57,360 --> 00:00:59,890
Remember that I want you to succeed.

14
00:00:59,910 --> 00:01:03,540
In fact that's why I'm giving you these guidelines in the first place.

15
00:01:03,690 --> 00:01:09,840
So if at any point when you're watching these lectures and you become confused just ask on the Q&amp;A.

16
00:01:09,840 --> 00:01:16,650
Also known as the discussion forum Typically I respond within hours sometimes even within minutes if

17
00:01:16,650 --> 00:01:20,170
I happen to be on the site and I see a notification.

18
00:01:20,340 --> 00:01:22,220
I answer any and all questions.

19
00:01:22,230 --> 00:01:25,860
So even if you think it's stupid just ask anyway.

20
00:01:26,340 --> 00:01:30,590
One example I get from time to time is where do I get the code for this course.

21
00:01:30,750 --> 00:01:35,460
And of course my answer is typically Well it's in the lecture called where to get the code for this

22
00:01:35,460 --> 00:01:36,320
course.

23
00:01:36,540 --> 00:01:40,760
At the end of the day no one cares if your question was trivial or silly.

24
00:01:40,860 --> 00:01:44,720
If it's something keeping you from progressing in the course I want to answer it.

25
00:01:49,610 --> 00:01:55,200
Now Very rarely I get people saying well I was so confused that I couldn't even think of the right question

26
00:01:55,220 --> 00:02:00,780
ask and this is where you have to take some responsibility for your own learning.

27
00:02:00,890 --> 00:02:06,360
You have to ask yourself what did the instructor assume I know that I didn't actually know.

28
00:02:06,830 --> 00:02:10,920
Maybe I can look into those things and that will help me formulate a question.

29
00:02:11,060 --> 00:02:16,490
Maybe there's some background knowledge I'm missing a lot of people like to have exercises to practice

30
00:02:16,550 --> 00:02:23,120
when they're taking a course the act of thinking of the right question to ask is itself an exercise.

31
00:02:23,300 --> 00:02:28,740
It might not be the type of exercise you thought you'd be doing but in many ways this is more profound.

32
00:02:28,760 --> 00:02:34,610
This is an exercise that requires you to think and to change how you think and ultimately that is the

33
00:02:34,610 --> 00:02:41,800
best value you can get out of a course.

34
00:02:41,820 --> 00:02:48,130
Speaking of background knowledge this is one of the most important guidelines in this lecture you may

35
00:02:48,130 --> 00:02:54,040
have noticed that in the course description I've listed some prerequisites or in other words things

36
00:02:54,040 --> 00:02:56,240
you should know before starting this course.

37
00:02:57,060 --> 00:03:00,160
Now you might wonder why do I ask you to know these things.

38
00:03:00,240 --> 00:03:05,700
Why don't I just teach them in the course and while we do review some topics in this course it's not

39
00:03:05,700 --> 00:03:07,030
the focus.

40
00:03:07,030 --> 00:03:12,680
There is such a wide variety of students in this Course students from almost every country in the world.

41
00:03:12,750 --> 00:03:15,860
Students of all ages students of all backgrounds.

42
00:03:15,960 --> 00:03:17,100
What does this mean.

43
00:03:17,940 --> 00:03:22,450
That means let's review for one person is going to be totally new for another.

44
00:03:22,470 --> 00:03:25,180
Some people are going to tell me they don't know calculus.

45
00:03:25,200 --> 00:03:29,310
Some people are going to be very far behind with their Python programming skills.

46
00:03:32,440 --> 00:03:38,290
But if we start teaching Python programming skills other people are going to say hey why are we doing

47
00:03:38,290 --> 00:03:38,940
Python.

48
00:03:39,010 --> 00:03:41,470
Isn't the topic of this course deep learning.

49
00:03:41,650 --> 00:03:44,300
And I tend to agree that we should stay on topic.

50
00:03:44,620 --> 00:03:50,990
So how can we reconcile this well it doesn't make sense for me to give you an entire computer science

51
00:03:50,990 --> 00:03:56,490
education in this one course because a lot of that would be irrelevant for a lot of people.

52
00:03:56,570 --> 00:04:02,150
The only logical thing to do is for all of us to meet at a common meeting point.

53
00:04:02,240 --> 00:04:03,680
How is that point defined.

54
00:04:03,950 --> 00:04:06,550
Well it's defined by the course prerequisites.

55
00:04:06,560 --> 00:04:12,800
In fact they are so important that in certain instances I've listed the cause prerequisites twice just

56
00:04:12,800 --> 00:04:14,710
in case you missed it the first time.

57
00:04:14,840 --> 00:04:21,880
And I'm also reminding you now for good measure.

58
00:04:21,920 --> 00:04:27,200
Now one pitfall is that people sometimes assume they know things that they don't really know.

59
00:04:27,200 --> 00:04:33,000
So if you took calculus 20 years ago and you got a C and you skipped class and the times that you did

60
00:04:33,000 --> 00:04:37,640
show up for class you were sleeping well probably you don't know that much calculus.

61
00:04:37,820 --> 00:04:40,030
But remember I want you to succeed.

62
00:04:40,250 --> 00:04:43,010
I want you to be able to learn this material.

63
00:04:43,040 --> 00:04:47,590
I can point you to resources where you can pick up this missing background knowledge.

64
00:04:47,750 --> 00:04:50,370
But the key is you have to ask.

65
00:04:50,530 --> 00:04:55,690
In some cases there are certain places where I'm not allowed to post certain links so we have to be

66
00:04:55,690 --> 00:04:58,470
mindful of the rules of the platform we're using.

67
00:05:03,270 --> 00:05:08,260
Now occasionally people ask me Well why don't you just teach a course for pure beginners.

68
00:05:08,730 --> 00:05:14,100
Why don't you teach these courses in such a way that they don't require lots of math and lots of prerequisites

69
00:05:15,190 --> 00:05:19,990
While I don't want to turn this into an easy beginner's type of course because for one that's not what

70
00:05:19,990 --> 00:05:21,690
I'm interested in personally.

71
00:05:21,910 --> 00:05:26,020
And number two don't forget that this is State of the art stuff.

72
00:05:26,020 --> 00:05:31,870
State of the art generally isn't easy and if it were easy that would mean everyone is doing it.

73
00:05:31,870 --> 00:05:36,760
And if a thousand other people can do the same thing as you well what's a potential employer going to

74
00:05:36,760 --> 00:05:37,430
think.

75
00:05:37,870 --> 00:05:43,120
What are your chances of getting that job when all 1000 of you have the exact same skills.

76
00:05:44,220 --> 00:05:46,640
So we don't want skills that are easy to get.

77
00:05:46,650 --> 00:05:51,960
We want skills that are hard to get skills that put you at the top of your game skills that not many

78
00:05:51,960 --> 00:05:53,210
people have.

79
00:05:53,220 --> 00:05:58,710
If I'm hiring someone I want the guy who stands out not the guy who says the same thing as everyone

80
00:05:58,710 --> 00:06:03,990
else.

81
00:06:04,000 --> 00:06:07,900
Finally the final guideline for how to succeed in this course.

82
00:06:08,170 --> 00:06:13,710
I mentioned earlier that there is a lot of material so much that it can be hard to keep track of.

83
00:06:13,750 --> 00:06:19,240
In addition to taking your own notes and doing all the derivations yourself how can you be absolutely

84
00:06:19,240 --> 00:06:21,940
sure you're understanding this material.

85
00:06:22,060 --> 00:06:26,110
I would in fact consider this even more important than the derivations.

86
00:06:26,110 --> 00:06:31,850
Not everyone is going to be a pro at math so it's understandable if you want to skip a few steps.

87
00:06:31,900 --> 00:06:37,480
Sometimes it's possible to compartmentalize some concepts or delegate learning them for some other time

88
00:06:37,990 --> 00:06:42,340
but still understanding the high level picture and how it fits in with everything else.

89
00:06:43,120 --> 00:06:46,380
What you cannot skip is the implementation.

90
00:06:46,380 --> 00:06:57,080
Implementing these algorithms in code is the real test for whether or not you understand the material.

91
00:06:57,140 --> 00:07:02,300
And this is not about reinventing the wheel or that you shouldn't roll your own whatever because someone

92
00:07:02,300 --> 00:07:04,460
else out there can do it better than you.

93
00:07:04,460 --> 00:07:09,900
That is a software engineering principle not a principle of learning in production.

94
00:07:09,920 --> 00:07:13,260
You don't want to write your own hash map or your own string class.

95
00:07:13,370 --> 00:07:19,590
And yet what do we usually do as an exercise in a typical intro to computer science class.

96
00:07:19,880 --> 00:07:21,540
Well we do precisely that.

97
00:07:21,590 --> 00:07:26,580
We implemented hash maps and we implement strings.

98
00:07:26,810 --> 00:07:28,390
And why do we do this.

99
00:07:28,730 --> 00:07:32,720
Because we want to have a better understanding of how these things work.

100
00:07:32,720 --> 00:07:38,510
If you make an assumption that's incorrect while your code is probably just not going to work merely

101
00:07:38,510 --> 00:07:44,750
using a hash map and using a string only gives you a very superficial understanding that's beginner

102
00:07:44,750 --> 00:07:51,010
stuff that's stuff everyone knows that's not stuff that's going to help you stand out from the competition.

103
00:07:51,170 --> 00:07:56,660
And it's true that you'll never use your own homemade hash map of your own homemade string in any code

104
00:07:56,660 --> 00:07:57,280
you write.

105
00:07:57,530 --> 00:08:01,520
Unless of course you are a professional that focuses on that sort of thing.

106
00:08:01,820 --> 00:08:06,950
They'll probably be inefficient and they'll probably have bugs but that's OK because you're not doing

107
00:08:06,950 --> 00:08:08,670
it to make it perfect.

108
00:08:08,750 --> 00:08:11,260
You're doing it to learn.

109
00:08:11,290 --> 00:08:16,420
You'll notice that the general pattern that this course follows is that we always discuss theory and

110
00:08:16,420 --> 00:08:18,450
then we implement that theory in code.

111
00:08:18,730 --> 00:08:23,060
So we're always going from theory to code implementing everything that we learned.

112
00:08:24,670 --> 00:08:31,310
If you can try to implement something before watching the coding lecture in the appendix I have a lecture

113
00:08:31,310 --> 00:08:33,330
called how to code by yourself.

114
00:08:33,500 --> 00:08:39,560
There goes much more in-depth into this topic along with multiple strategies for how to approach implementation

115
00:08:39,560 --> 00:08:45,260
exercises.

116
00:08:45,280 --> 00:08:50,820
So to summarize these are the guidelines I think are going to help you succeed in this course.

117
00:08:50,830 --> 00:08:58,260
Number one make generous use of the Q&amp;A even when you can't think of the right question ask.

118
00:08:58,320 --> 00:09:02,320
Number two make sure you meet the prerequisites to this course.

119
00:09:02,460 --> 00:09:09,940
If you're not sure what they are or you're not sure how C guideline number one number three try your

120
00:09:09,940 --> 00:09:10,330
best.

121
00:09:10,360 --> 00:09:12,390
Implement everything we learn.

122
00:09:12,400 --> 00:09:15,480
This is the true test for whether or not you understand something.

123
00:09:17,460 --> 00:09:23,220
Remember that it's perfectly normal to get stuck once in a while I get stuck all the time when I'm learning.

124
00:09:23,220 --> 00:09:24,940
That doesn't mean I'm not smart.

125
00:09:25,170 --> 00:09:28,510
Nor does it mean the book or video I'm learning from is bad.

126
00:09:28,560 --> 00:09:33,780
It means that there is a disconnect between what the author believes I knew and what I actually know

127
00:09:34,460 --> 00:09:41,770
and as a learner I do my best to close that gap a good skill to have is learning how to compartmentalize

128
00:09:41,770 --> 00:09:42,850
concepts.

129
00:09:42,850 --> 00:09:44,950
So here are the things I understand.

130
00:09:44,950 --> 00:09:46,670
Here are the things I don't understand.

131
00:09:46,810 --> 00:09:50,100
But here are the things I understand about the things I don't understand.

132
00:09:50,290 --> 00:09:52,150
And these are the holes.

133
00:09:52,270 --> 00:09:56,440
So you know what you're missing and you know where they fit and you can work to fill in those gaps over

134
00:09:56,440 --> 00:09:57,230
time.

135
00:09:58,040 --> 00:10:03,300
One thing I've been doing quite a bit recently is adding review lectures to my courses.

136
00:10:03,320 --> 00:10:08,180
These aren't meant to teach you everything from scratch since that's going to take you a long time but

137
00:10:08,180 --> 00:10:11,700
they are meant to help you recall certain things you may have forgotten.

138
00:10:11,750 --> 00:10:17,240
So if you have an idea for a review lecture that you'd like to see added to this course please feel

139
00:10:17,240 --> 00:10:19,220
free to make a suggestion using the Q&amp;A.
