1
00:00:00,240 --> 00:00:06,640
so at some point after robots take all of our jobs they'll eventually decide

2
00:00:04,560 --> 00:00:10,320
that the world just really doesn't need humans that badly and will do away with

3
00:00:08,960 --> 00:00:15,120
us all together but then haven't you ever wondered how

4
00:00:13,120 --> 00:00:19,279
this incredibly rosy vision of the future will come to pass

5
00:00:16,960 --> 00:00:24,960
well i can tell you that it'll probably involve neural networks now we tend to

6
00:00:21,840 --> 00:00:27,119
think of artificial intelligence as the

7
00:00:24,960 --> 00:00:32,480
capability of a computer to make sensible decisions on its own kind of

8
00:00:29,679 --> 00:00:36,880
like a human and as it turns out it's more human-like than you actually might

9
00:00:34,719 --> 00:00:42,320
think computer scientists and programmers have modeled the way that

10
00:00:39,680 --> 00:00:48,559
computers arrive at their decisions after our own brains at least to a point

11
00:00:45,840 --> 00:00:53,920
so inside your nervous system your neurons are arranged in such a way that

12
00:00:51,120 --> 00:00:59,039
after information is taken in one group of neurons will pass that information to

13
00:00:56,399 --> 00:01:02,559
the next group in a way that depends on what signals the previous group was

14
00:01:01,280 --> 00:01:07,840
sending okay so for example then if neurons in

15
00:01:05,119 --> 00:01:10,799
your muscles sense that they're working really hard because you're going out for

16
00:01:09,840 --> 00:01:16,240
a run those neurons send out signals through a

17
00:01:13,520 --> 00:01:21,759
specific pathway that ultimately results in your brain telling your diaphragm to

18
00:01:19,040 --> 00:01:25,119
breathe harder rather than you know send a message to your hair to grow

19
00:01:24,000 --> 00:01:30,560
faster and although the way that our neurons

20
00:01:27,439 --> 00:01:32,640
work is immensely more complicated than

21
00:01:30,560 --> 00:01:37,200
an artificial neural network made up of ones and zeros the neural networks used

22
00:01:35,040 --> 00:01:43,759
in machine learning are at least loosely based on the workings of your brain

23
00:01:41,040 --> 00:01:49,280
instead of neurons made up of dna and cytoplasm though a software neural

24
00:01:46,159 --> 00:01:52,320
network uses processing nodes stacked

25
00:01:49,280 --> 00:01:54,720
into many different layers so a node in

26
00:01:52,320 --> 00:01:58,560
the first layer which initially receives the data

27
00:01:55,759 --> 00:02:03,200
weights all of its incoming connections by multiplying each piece of data by a

28
00:02:01,360 --> 00:02:07,759
certain factor depending on the connection it then adds these numbers

29
00:02:05,600 --> 00:02:12,239
together and if it's above a certain threshold the node sends it along to a

30
00:02:09,679 --> 00:02:15,920
node in the next layer and then so on and so forth

31
00:02:13,680 --> 00:02:20,879
once the data gets to the end of the neural network the network has

32
00:02:17,680 --> 00:02:23,120
effectively made a decision based on

33
00:02:20,879 --> 00:02:26,800
weighting this combined and then recombined data across many of these

34
00:02:25,680 --> 00:02:31,120
layers now all of this probably sounds quite

35
00:02:29,680 --> 00:02:37,200
abstract but basically neural networks use thousands or

36
00:02:34,640 --> 00:02:42,000
millions of these nodes to turn those numbers into something useful

37
00:02:39,680 --> 00:02:46,239
of course even the most sophisticated neural network isn't going to know right

38
00:02:44,239 --> 00:02:51,519
off the bat how to differentiate a picture of a burrito from a body pillow

39
00:02:49,360 --> 00:02:54,480
just like a baby doesn't pop out of the womb already knowing how to speak the

40
00:02:53,040 --> 00:03:00,640
king's english so instead developers train a neural

41
00:02:57,840 --> 00:03:06,640
network by feeding it lots and lots of both relevant and irrelevant inputs so

42
00:03:04,159 --> 00:03:11,599
for something like a self-driving car it might be a ton of images including some

43
00:03:09,680 --> 00:03:16,400
of pickup trucks as the data gets fed into the network

44
00:03:13,760 --> 00:03:20,879
developers monitor its behavior and then adjust the weights on the processing

45
00:03:18,720 --> 00:03:26,080
nodes until the desired output is reached and the system can eventually

46
00:03:23,200 --> 00:03:31,200
quickly differentiate a truck from a bicycle or baby stroller or stationary

47
00:03:29,280 --> 00:03:36,560
object or what have you the whole idea is very general purpose

48
00:03:34,080 --> 00:03:40,000
so it can actually be adapted to lots of different situations

49
00:03:38,159 --> 00:03:44,319
other than the more well-known examples that we've already discussed like image

50
00:03:41,840 --> 00:03:48,640
recognition and autonomous vehicles neural networks have been used for

51
00:03:45,920 --> 00:03:52,799
everything from filtering spam out of email to training computers to play

52
00:03:50,879 --> 00:03:58,000
video games nearly as well as professional level human players

53
00:03:55,200 --> 00:04:02,319
of course training a computer to think is more complicated than getting it to

54
00:03:59,840 --> 00:04:06,720
run a bunch of pre-defined instructions and as such training a neural network

55
00:04:04,640 --> 00:04:11,439
can be quite time consuming and depending on the application requires

56
00:04:08,799 --> 00:04:15,599
some pretty powerful hardware in fact the computers in current self-driving

57
00:04:13,280 --> 00:04:21,680
cars are not only more powerful than your standard desktop pc they are

58
00:04:18,320 --> 00:04:23,520
notorious battery hogs but as processors

59
00:04:21,680 --> 00:04:29,440
become more efficient and our training methods become less tedious we fully

60
00:04:26,080 --> 00:04:32,240
expect that one day our cars and spam

61
00:04:29,440 --> 00:04:36,800
filters might be even smarter than we are so even if they do decide to turn on

62
00:04:34,800 --> 00:04:41,360
us take over the world and rule in tyranny at least we won't have to deal

63
00:04:39,040 --> 00:04:45,199
with scam emails from nigerian princes or terrible drivers anymore

64
00:04:43,440 --> 00:04:49,199
private internet access supports a variety of vpn protocols and types of

65
00:04:47,520 --> 00:04:53,440
encryption and authentication to allow you to dial in the exact level of

66
00:04:51,120 --> 00:04:58,479
privacy protection that you need they've got apps for Windows macOS Android iOS

67
00:04:56,240 --> 00:05:02,639
Linux and google chrome with support for other platforms coming you can connect

68
00:05:00,720 --> 00:05:07,360
up to five devices at the same time with a single account and their apps include

69
00:05:04,639 --> 00:05:12,080
features like dns leak protection ipv6 leak protection and an internet kill

70
00:05:09,680 --> 00:05:15,840
switch that will block all traffic if the vpn becomes disconnected

71
00:05:13,759 --> 00:05:20,000
unexpectedly so check it out today at the link in the video description

72
00:05:18,240 --> 00:05:23,120
so thanks for watching guys like dislike check out our other videos leave a

73
00:05:21,600 --> 00:05:28,400
comment if you have a suggestion for a future fast as possible episode and

74
00:05:25,520 --> 00:05:32,479
don't forget to subscribe to techwiki and ring the bell you look really

75
00:05:30,479 --> 00:05:35,280
closely make sure it's wrong ringed

76
00:05:33,680 --> 00:05:38,280
wrong right