1
00:00:02,570 --> 00:00:08,230
Everyone and welcome back to this class.

2
00:00:08,250 --> 00:00:13,620
This is a short lecture I like to give in each of my courses on how to succeed in this course.

3
00:00:13,620 --> 00:00:18,330
This is very important to talk about because you're learning a difficult technical subject.

4
00:00:18,510 --> 00:00:23,250
It's easy to get stuck or even worse give up because you're just not getting things.

5
00:00:23,400 --> 00:00:27,120
Maybe there are too many gaps in your knowledge so you can't connect the dots.

6
00:00:27,180 --> 00:00:30,450
Maybe some assumptions you've made is incorrect.

7
00:00:30,450 --> 00:00:33,400
And keep in mind there's a lot of material in this course.

8
00:00:33,450 --> 00:00:38,760
It can be overwhelming if you're new to this field of study and you're not familiar with the conventions

9
00:00:38,760 --> 00:00:41,560
any typical patterns we use.

10
00:00:41,600 --> 00:00:47,060
Now if you've already seen this lecture in the past you're more than welcome to skip it if you remember

11
00:00:47,060 --> 00:00:54,890
what's in it and you're already using these guidelines.

12
00:00:55,040 --> 00:00:59,770
The first guideline is this remember that I want you to succeed.

13
00:00:59,930 --> 00:01:03,570
In fact that's why I'm giving you these guidelines in the first place.

14
00:01:03,710 --> 00:01:09,410
So if at any point when you're watching these lectures and you become confused just ask on the Q and

15
00:01:09,410 --> 00:01:16,460
A also known as the discussion forum typically I respond within hours sometimes even within minutes

16
00:01:16,490 --> 00:01:18,220
if I happen to be on the site.

17
00:01:18,350 --> 00:01:20,100
And I see a notification.

18
00:01:20,360 --> 00:01:22,250
I answer any and all questions.

19
00:01:22,250 --> 00:01:26,230
So even if you think it's stupid just ask anyway.

20
00:01:26,360 --> 00:01:30,770
One example I get from time to time is where do I get the code for this course.

21
00:01:30,770 --> 00:01:35,480
And of course my answer is typically well it's in the lecture called where to get the code for this

22
00:01:35,480 --> 00:01:37,730
course at the end of the day.

23
00:01:37,940 --> 00:01:42,830
No one cares if your question was trivial or silly if it's something keeping you from progressing in

24
00:01:42,830 --> 00:01:44,510
the course I want to answer it

25
00:01:49,610 --> 00:01:55,210
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 --> 00:02:00,880
ask and this is where you have to take some responsibility for your own learning.

27
00:02:00,920 --> 00:02:06,800
You have to ask yourself what did the instructor assume I know that I didn't actually know.

28
00:02:06,860 --> 00:02:10,940
Maybe I can look into those things and that will help me formulate a question.

29
00:02:11,060 --> 00:02:16,520
Maybe there's some background knowledge I'm missing a lot of people like to have exercises to practice

30
00:02:16,550 --> 00:02:18,220
when they're taking a course.

31
00:02:18,400 --> 00:02:23,330
The act of thinking of the right question to ask is itself an exercise.

32
00:02:23,330 --> 00:02:28,720
It might not be the type of exercise you thought you'd be doing but in many ways this is more profound.

33
00:02:28,760 --> 00:02:33,140
This is an exercise that requires you to think and to change how you think.

34
00:02:33,140 --> 00:02:41,800
And ultimately that is the best value you can get out of a course.

35
00:02:41,820 --> 00:02:47,670
Speaking of background knowledge this is one of the most important guidelines in this lecture.

36
00:02:47,880 --> 00:02:53,520
You may have noticed that in the course description I've listed some prerequisites or in other words

37
00:02:53,790 --> 00:02:57,030
things you should know before starting this course.

38
00:02:57,080 --> 00:03:00,150
Now you might wonder why do I ask you to know these things.

39
00:03:00,270 --> 00:03:02,630
Why don't I just teach them in the course.

40
00:03:02,640 --> 00:03:06,970
And while we do review some topics in this course it's not the focus.

41
00:03:07,050 --> 00:03:09,990
There's such a wide variety of students in this course.

42
00:03:10,110 --> 00:03:12,560
Students from almost every country in the world.

43
00:03:12,750 --> 00:03:15,960
Students of all ages students of all backgrounds.

44
00:03:15,990 --> 00:03:16,890
What does this mean.

45
00:03:17,930 --> 00:03:22,480
That means what's review for one person is going to be totally new for another.

46
00:03:22,490 --> 00:03:25,220
Some people are going to tell me they don't know calculus.

47
00:03:25,220 --> 00:03:28,940
Some people are going to be very far behind with their Python programming skills

48
00:03:32,430 --> 00:03:38,310
but if we start teaching Python programming skills other people are going to say hey why are we doing

49
00:03:38,310 --> 00:03:39,040
Python.

50
00:03:39,060 --> 00:03:44,430
Isn't the topic of this course deep learning and I tend to agree that we should stay on topic.

51
00:03:44,640 --> 00:03:47,860
So how can we reconcile this.

52
00:03:47,860 --> 00:03:52,930
Well it doesn't make sense for me to give you an entire computer science education in this one course

53
00:03:53,290 --> 00:03:56,510
because a lot of that would be irrelevant for a lot of people.

54
00:03:56,560 --> 00:04:02,180
The only logical thing to do is for all of us to meet at a common meeting point.

55
00:04:02,260 --> 00:04:03,970
How is that point defined.

56
00:04:03,970 --> 00:04:06,510
Well it's defined by the course prerequisites.

57
00:04:06,580 --> 00:04:12,850
In fact they are so important that in certain instances I've listed the course prerequisites twice just

58
00:04:12,850 --> 00:04:14,860
in case you missed it the first time.

59
00:04:14,860 --> 00:04:21,910
And I'm also reminding you now for good measure.

60
00:04:21,940 --> 00:04:27,220
Now one pitfall is that people sometimes assume they know things that they don't really know.

61
00:04:27,220 --> 00:04:33,020
So if you took calculus 20 years ago and you got a C and you skipped class and the times that you did

62
00:04:33,020 --> 00:04:37,810
show up for class you were sleeping well probably you don't know that much calculus.

63
00:04:37,810 --> 00:04:40,180
But remember I want you to succeed.

64
00:04:40,270 --> 00:04:43,040
I want you to be able to learn this material.

65
00:04:43,090 --> 00:04:48,520
I can point you to resources where you can pick up this missing background knowledge but the key is

66
00:04:48,520 --> 00:04:55,000
you have to ask in some cases there are certain places where I'm not allowed to post certain links.

67
00:04:55,050 --> 00:04:58,290
So we have to be mindful of the rules of the platform we are using

68
00:05:03,300 --> 00:05:03,510
now.

69
00:05:03,510 --> 00:05:08,590
Occasionally people ask me Well why don't you just teach a course for pure beginners.

70
00:05:08,730 --> 00:05:15,210
Why don't you teach these courses in such a way that they don't require lots of math and lots of prerequisites.

71
00:05:15,210 --> 00:05:20,010
Well I don't want to turn this into an easy beginners type of course because for one that's not what

72
00:05:20,010 --> 00:05:21,880
I'm interested in personally.

73
00:05:21,930 --> 00:05:28,500
And number two Don't forget that this is State of the art stuff State of the art generally isn't easy.

74
00:05:28,590 --> 00:05:31,400
And if it were easy that would mean everyone is doing it.

75
00:05:31,920 --> 00:05:34,650
And if a thousand other people can do the same thing as you.

76
00:05:35,100 --> 00:05:41,010
Well what's a potential employer going to think what are your chances of getting that job when all 1000

77
00:05:41,010 --> 00:05:46,490
of you have the exact same skills so we don't want skills that are easy to get.

78
00:05:46,640 --> 00:05:51,980
We want skills that are hard to get skills that puts you at the top of your game skills that not many

79
00:05:51,980 --> 00:05:52,670
people have.

80
00:05:53,240 --> 00:06:03,990
If I'm hiring someone I want the guy who stands out at the guy who says the same thing as everyone else.

81
00:06:04,020 --> 00:06:08,060
Finally the final guideline for how to succeed in this course.

82
00:06:08,190 --> 00:06:13,710
I mentioned earlier that there's a lot of material so much that it can be hard to keep track of.

83
00:06:13,780 --> 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 --> 00:06:22,050
sure you're understanding this material.

85
00:06:22,090 --> 00:06:26,060
I would in fact consider this even more important than the derivations.

86
00:06:26,140 --> 00:06:28,140
Not everyone is going to be a pro at math.

87
00:06:28,450 --> 00:06:31,690
So it's understandable if you want to skip a few steps.

88
00:06:31,930 --> 00:06:37,480
Sometimes it's possible to compartmentalize some concepts or delegate learning them for some other time

89
00:06:37,990 --> 00:06:43,850
but still understanding be high level picture and how it fits in with everything else what you cannot

90
00:06:43,850 --> 00:06:46,270
skip is the implementation.

91
00:06:46,400 --> 00:06:52,120
Implementing these algorithms in code is the real test for whether or not you understand the material

92
00:06:57,160 --> 00:07:02,320
and this is not about reinventing the wheel or that you shouldn't roll your own whatever because someone

93
00:07:02,320 --> 00:07:04,480
else out there can do it better than you.

94
00:07:04,480 --> 00:07:09,970
That is a software engineering principle not a principle of learning in production.

95
00:07:09,970 --> 00:07:15,490
You don't want to write your own hash map or your own string class and yet what do we usually do as

96
00:07:15,490 --> 00:07:19,900
an exercise in a typical Intro to Computer Science class.

97
00:07:19,900 --> 00:07:21,460
Well we do precisely that.

98
00:07:21,610 --> 00:07:26,770
We implement hash maps and we implement strings.

99
00:07:26,860 --> 00:07:28,530
And why do we do this.

100
00:07:28,720 --> 00:07:32,650
Because we want to have a better understanding of how these things work.

101
00:07:32,740 --> 00:07:35,020
If you make an assumption that's incorrect.

102
00:07:35,050 --> 00:07:37,890
Well your code is probably just not going to work.

103
00:07:38,140 --> 00:07:43,870
Merely using a hash map and using a string only gives you a very superficial understanding.

104
00:07:44,050 --> 00:07:49,240
That's beginner's stuff that stuff everyone knows that's not stuff that's going to help you stand out

105
00:07:49,240 --> 00:07:51,050
from the competition.

106
00:07:51,220 --> 00:07:56,680
And it's true that you'll never use your own homemade hash map or your own homemade string in any code

107
00:07:56,680 --> 00:08:01,720
you write unless of course you are a professional that focuses on that sort of thing.

108
00:08:01,840 --> 00:08:06,970
They'll probably be inefficient and they'll probably have bugs but that's OK because you're not doing

109
00:08:06,970 --> 00:08:08,620
it to make it perfect.

110
00:08:08,770 --> 00:08:14,700
You're doing it to learn you'll notice that the general pattern that this course follows is that we

111
00:08:14,700 --> 00:08:20,250
always discuss theory and then we implement that theory in code so we're always going from theory to

112
00:08:20,250 --> 00:08:27,970
code implementing everything that we learned if you can try to implement something before watching the

113
00:08:27,970 --> 00:08:30,730
coding lecture in the appendix.

114
00:08:30,730 --> 00:08:33,470
I have a lecture called how to code by yourself.

115
00:08:33,520 --> 00:08:39,580
That goes much more in-depth into this topic along with multiple strategies for how to approach implementation

116
00:08:39,580 --> 00:08:40,390
exercises

117
00:08:45,300 --> 00:08:46,650
So to summarize.

118
00:08:46,710 --> 00:08:50,830
These are the guidelines I think are going to help you succeed in this course.

119
00:08:50,850 --> 00:08:58,580
Number one make generous use of the Q and A even when you can't think of the right question ask number

120
00:08:58,580 --> 00:09:02,360
two make sure you meet the prerequisites to this course.

121
00:09:02,480 --> 00:09:08,250
If you're not sure what they are or you're not sure how C guideline number one.

122
00:09:08,400 --> 00:09:09,500
Number three.

123
00:09:09,540 --> 00:09:11,800
Try your best implement everything we learned.

124
00:09:12,390 --> 00:09:17,410
This is the true test for whether or not you understand something.

125
00:09:17,460 --> 00:09:23,070
Remember that it's perfectly normal to get stuck once in a while I get stuck all the time when I'm learning.

126
00:09:23,220 --> 00:09:28,520
That doesn't mean I'm not smart nor does it mean the book or video I'm learning from is bad.

127
00:09:28,590 --> 00:09:33,810
It means that there's a disconnect between what the author believes I knew and what I actually know

128
00:09:34,530 --> 00:09:41,780
and as a learner I do my best to close that gap a good skill to have is learning how to compartmentalize

129
00:09:41,780 --> 00:09:42,840
concepts.

130
00:09:42,860 --> 00:09:44,860
So here are the things I understand.

131
00:09:44,990 --> 00:09:46,750
Here are the things I don't understand.

132
00:09:46,820 --> 00:09:50,200
But here are the things I understand about the things I don't understand.

133
00:09:50,300 --> 00:09:54,590
And these are the holes so you know what you're missing and you know where they fit.

134
00:09:54,800 --> 00:10:01,070
And you can work to fill in those gaps over time one thing I've been doing quite a bit recently is adding

135
00:10:01,070 --> 00:10:03,260
review lectures to my courses.

136
00:10:03,320 --> 00:10:08,210
These are meant to teach you everything from scratch since that's going to take you a long time but

137
00:10:08,210 --> 00:10:11,660
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 --> 00:10:19,250
free to make a suggestion using the Q and A.
