Original subtitles

1 1

Hello and welcome to the Intuition tutorials 2

2

for the artificial neural networks part of the course. 3

3

Super excited to get these things started 4

4

and today we're going to find out 5

5

how we're going to tackle this section. 6

6

So, in this section we will learn the following things. 7

7

First of all we'll talk about the neurons 8

8

so there'll be a little bit of neuroscience 9

9

and we'll find out a bit about how the human brain works 10

10

and why we're trying to replicate that 11

11

and we'll also see what the main building block 12

12

of a neural network, the neuron, looks like. 13

13

Then in the next tutorial we'll talk about 14

14

the activation function and we'll look at 15

15

a couple of examples of activation functions 16

16

that you could use in your neural networks 17

17

and we'll find out which ones of 18

18

which one of them is 19

19

the most commonly used one 20

20

in neural networks and 21

21

in which layers you would rather use which functions. 22

22

Then we'll talk about how neural networks work so 23

23

in contrast to what you would expect 24

24

and what was probably conveyed in other 25

25

courses and tutorials, 26

26

we're not going to go into the learning 27

27

we're actually going to go into the working 28

28

of the neural networks first. 29

29

Because that way, by seeing a neural network in action 30

30

that'll allow us to understand what we're 31

31

aiming towards, what our goal is 32

32

so here we'll look at an example of a neural network 33

33

we're going to look at a 34

34

a very simplified, very simplified hypothetical example 35

35

of a neural network working 36

36

to predict housing prices 37

37

so basically real estate prices 38

38

and by looking at that example we'll understand better 39

39

exactly what we're aiming towards 40

40

and what we want to achieve in the end. 41

41

And then we will move on to 42

42

understanding how neural networks learn 43

43

because that way we'll be more prepared for what's coming. 44

44

Then we'll talk about gradient descent. 45

45

This is also part of neural networks' learning 46

46

and we'll understand how that algorithm is 47

47

better than just the brute force method 48

48

that you might 49

49

be intending or willing to take as a first resort 50

50

or first method that comes to mind, so. 51

51

We'll find out how great, what the advantage 52

52

of gradient descent are. 53

53

And then we'll talk about stochastic gradient descent. 54

54

It's a continuation of the gradient descent tutorial 55

55

but it's an even better and even stronger method 56

56

and we'll find out exactly how it works. 57

57

And finally we'll wrap things up by 58

58

mentioning the important things about backpropagation 59

59

and summarizing everything in a step-by-step 60

60

set of instructions for running 61

61

your artificial neural networks. 62

62

I hope this all sounds very exciting to you 63

63

because I am very excited myself, 64

64

and I can't wait to get started. 65

65

I look forward to seeing you on the first tutorial 66

66

and until then, enjoy deep learning.