Original subtitles

1

Arrive exciting tutorial ahead.

2

Welcome back to the course on deep learning.

3

Today we're talking about how neural networks work.

4

Now we've led a lot of ground work we've talked about how neural networks are structured what elements

5

they consist of and even their functionality.

6

And today we're going to look at and a real example of how unusual neural network can be applied and

7

we're actually going to work step by step through the process of its application so we know what is

8

going on.

9

So let's have a look what example we're going to be talking about.

10

We're going to be looking at a property evaluation so we're going to look at a neural network that takes

11

in some parameters of our property and value values.

12

And the thing here.

13

There's a small caveat for today's tutorial and that is we're not actually going to train the network.

14

So a very important part in neural networks is training them up and we're going to look at that in the

15

next tutorials in this section.

16

For now we're going to focus on actual applications are we going to work with a neural network that

17

we're going to pretend is already trained up and that will allow us to focus on the application side

18

of things and not get bogged down in the training aspect and then we'll cover off the training when

19

we already know the end goal we're working towards.

20

Sounds good.

21

All right let's jump straight into it.

22

So let's say we have some input parameters.

23

Right so let's say we have full parameters about the property we have area in square feet we have the

24

number of bedrooms that distance the city and Miles the New York City and the age of the property and

25

all of those four are going to comprise our inputs layer.

26

Now of course they're probably way more parameters that define the price of a property but for simplicity

27

sake we're going to look at just this for now.

28

It's very basic form a neural network only has an input learn an output layer so no hidden layers and

29

our output layer is the price that we're predicting.

30

So in this form what these inputs variables would do is they would just be weighted up by the synopses

31

and then the output there would be calculated.

32

Basically the price would be calculated and would get a price.

33

And for instance the price could be calculated as simple as the weighted sum of all of the inputs.

34

And again here you could use pretty much any function you could use.

35

What we're using now we could use any of the activation functions we had previously you could use logistic

36

regression.

37

You could use a squared function you can do pretty much anything here but the point is that you get

38

a certain output.

39

And moreover most of the machine learning algorithms that exist can be represented in this form and

40

this is basically a diagrammatic representation of how you deal with the variables or by changing the

41

way it's a formalised you can accomplish quite a lot of the machine learning algorithms that we've talked

42

about before and put them into this form and that just tends to show how powerful Noul are neural networks

43

are.

44

Even without the hidden layers we are ready where we have a representation that works for most other

45

machine learning algorithms.

46

But in neural networks what we do have is an advantage that gives us lots of flexibility and power which

47

is where that increase in accuracy comes from.

48

And that power is the hidden layers and there we go that's our hit Alair we added it in and now we're

49

going to understand how that hidden lair gives us that extra power.

50

And in fact to do that we're going to walk through an example so as we agreed this neural network has

51

really been trained up and now we're just going to plug in we're going to imagine they were plugging

52

in a property and we're going to walk step by step through how the neural network will deal with the

53

input variables and calculate the Hindol area and then calculate the output.

54

So let's go through this is going to be exciting.

55

All right.

56

We've got all four variables on the left and we're going to first start with the top Nurin on the Hindle

57

there.

58

Now as we previously saw in the press literals all of the neurons from the input layer they have Cynapsus

59

connecting it to each one of them to the top neuron in the hidden lair.

60

And those systems have weights.

61

Now let's agree that some weights will have a non-zero value some ways will have zero value because

62

basically not all inputs will be valid or not all inputs will be important for every single neuron sometimes

63

inputs will not be important.

64

Here we can see two examples that X-1 next three the area and the distance to the city and Miles are

65

important for that neuron whereas bedrooms and age are not like let's think about this for a second

66

why how would that be the case.

67

Like why would a neuron be linked to the area and the distance what does that what could that mean.

68

Well that could mean that normally the further away you get from the city the cheaper real estate becomes

69

and therefore the space in square feet of properties becomes larger.

70

So for the same price you can get a larger property the further away you go from the city that's normal

71

right.

72

That that makes sense and probably what this neuron is doing is it is looking specifically it's like

73

like a sniper it's looking for area properties which have which are not so far from the city but have

74

a large area.

75

So for their distance from the city they have an unfair square foot area.

76

Right so something as abnormals height is higher than average so they're quite close to the city but

77

they're still large as opposed to the other ones at the same distance and so that neuron again we're

78

speculating here but that neuron might be picking up laser picking out those specific properties and

79

it will activate and hence the activation function it will activate it'll fire up only when the certain

80

criteria is met that you know the distance and the area of the proper distance to Syrian air of the

81

area of the property and it performs on calculations inside itself and it combines those two and as

82

soon as certain areas where it fires up and that contributes to the price in output.

83

And therefore this neuron doesn't really care about bedrooms and age of the property because it's focused

84

on that specific thing.

85

That's where the power of the neural network comes from because you have many of these years and will

86

see just now how the other ones work.

87

But what I want to agree here is that let's not even draw these lines for the synopses that are not

88

in place so that we don't clutter up our image as the only reason we're not going to draw them so let's

89

just get rid of those too.

90

And that way we will know exactly OK so this neuron is focused on area and distance to the city.

91

All right.

92

So as always we agree on that.

93

Let's move on to next.

94

Let's take them one in the middle here we've got three parameters feeding into this neuron so we've

95

got the area the bedrooms and the age of the property.

96

So what could be the reason here.

97

Let's again let's try to understand the intuition and the thinking of this neuron how is this neuron

98

thinking.

99

Why is it picking these two parents.

100

What could it be what could have a hit like found in the data.

101

Right so we've already established this trained up data set the training has happened a long time ago

102

maybe like a day ago or somebody is written up as it is now we're just applying and we know that this

103

neuron through all of the thousands of examples of properties has found out that the area plus the bedrooms

104

plus the age combination of those parameters is important.

105

Why could that be the case.

106

Well for instance maybe in that specific city in those suburbs that this neural network has been trained

107

up in perhaps there's a lot of families with kids who have two or more children who are looking for

108

large properties with lots of bedrooms but which are new rights which are not old proper because maybe

109

that's in that area almost appropriate or kind of like big properties are usually old.

110

But there's lots of modern families and maybe there has been a social demographic shift and or maybe

111

there's been like a lot of like some growth in terms of employment and jobs for the younger self population

112

maybe just you know the like the population demographics have changed and now younger couples or younger

113

families are looking for properties but they prefer new properties so they want the age of the property

114

to be lower and hence from the training that this neural network has undergone.

115

It knows that when there's a property with a large area and with lots of bedroom with these three at

116

least three bedrooms for the parents for the first of the second child for at least three bedrooms maybe

117

a guest room when you property with high area and lots of bedrooms that is valued that in that market

118

that is valuable so that Meuron has picked that up.

119

It knows that.

120

OK so this is what I'm going to be looking for.

121

I don't care about the distance to the city and Miles wherever it is as long as it has high area lots

122

of bedrooms.

123

As soon as that criteria is met the neuron fires up and the combination of these two parameters and

124

this is again this is where the power of the neural network is coming from because it combines these

125

two parameters into a brand new parameter into brand new attributes.

126

That helps with the evaluation that helps with the valuation of the property.

127

It combines them into a new attribute and therefore it's more precise.

128

So there we go that's how that works.

129

And let's look at another one let's look at the very bottom one for instance this neuron could be could

130

even have picked up just one pair and that it could have just picked up eight and not in any of the

131

other ones.

132

And how could that be the case.

133

Well this is a classic example of when age could mean like as we all know the older properties usually

134

it's less valuable because it's worn out.

135

Probably the building is old probably you know things are falling apart.

136

More maintenance is required so the price drops in terms of the price of the real estate.

137

Whereas a brand new building it would be more expensive because it's brand new.

138

Perhaps if a property is over a certain age that could indicate that it's a historic property.

139

For instance if a property is under 100 years old then the older it is the less valuable it is.

140

But as soon as it jumps over 100 years old all of a sudden it becomes a historic property because this

141

is a property where people still have hundreds of years ago.

142

It tells a story it's got all this history behind it and some people like that some people value that.

143

In fact quite a lot of people would like that and would be proud to live in a property and especially

144

in the higher socioeconomic classes they would they would show off to their friends or things like that

145

and therefore properties that are over 100 years old could be deemed as historic.

146

And therefore this neuron as soon as it sees a property over 100 years old it'll fire up and contribute

147

to the overall price.

148

And otherwise if it's under 100 years old then it won't work and this is a good example of that.

149

The rectifier function being applied.

150

So here you've got like a very like a zero until a certain point and then let's say 100 years old and

151

then after 100 years old the older it gets the higher the value the higher the contribution of this

152

neuron to the overall price.

153

And there's just a wonderful example of a very simple example of this rectifier function in action.

154

So there we go.

155

That could be this year.

156

And moreover the neural network could have picked up things that we wouldn't have thought of ourselves

157

right.

158

For instance bedrooms plus distance the city maybe that's in combination somehow contributes to the

159

price maybe not as strong as the other neurons and it contributes but it still contributes or maybe

160

it detracts from the price that could also be the case or other things like that and maybe add your

161

own picked up all for a combination of all four of these parameters and as you can see that these neurons

162

this whole hidden layer situation allows you to increase the flexibility of your neural network and

163

allows you to really allows the neural network to look for very specific things and then in combination

164

that's where the power comes from.

165

It's like that example the answer I'd like an ad by itself cannot build an anthill.

166

But when you have like a thousand or 100000 ads they can build an anthill together and that's that's

167

the situation here.

168

Each one of these neurons by itself cannot predict the price.

169

But together they have super powers and they predict the price and they can do quite an accurate job

170

if trained properly set up properly.

171

And that's what this whole Course is about understanding how to utilize them.

172

There we go so that is a step by step example and walkthrough of how neural networks actually work.

173

I hope you enjoyed today's tutorial and I can't wait to see you next time.

174

Until then enjoy learning.