Lecture 04: Data Science vs Machine Learning vs AI

Nafees AI Lab

A conceptual comparison of Data Science, Machine Learning and AI. #DS #ML #AI

Transcript

00:00Welcome back, Shizaday and Shizadiyo.

00:05So, our first time was a smart shopkeeper.

00:08We saw a smart shopkeeper.

00:10We deployed an algorithm to get the customer needs to understand.

00:15So, let's see how the data science is.

00:20And the predictive work of the shopkeeper.

00:25We can see in detail that this is basically science.

00:29So, our first time was the data science.

00:32Data science.

00:33So, in this lecture, we can see what data science is basically.

00:37Okay.

00:38Then we can see that data science is another field.

00:41It is called machine learning.

00:45And then we can see that machine learning is our own.

00:49Artificial intelligence is called artificial intelligence.

00:56Okay.

00:57Now, let's talk about data science.

01:00So, let's talk about data science.

01:03Okay.

01:04I can see data science.

01:05Okay.

01:06Now, data science is like data science, data science.

01:10Data science is data science.

01:14Data science is data science.

01:15that data can exist in science.

01:20Data should be data.

01:22Data should be data.

01:24One is data. Excellent.

01:26The other thing, when we say science is

01:28that it means that

01:30there is no action to perform.

01:33He says rocket and do it.

01:36This is science.

01:38It means that there is no action to perform.

01:40Two things you might have left.

01:42Data science means that

01:43there is no action to perform.

01:45What is data?

01:47Data science means that is very simple.

01:49Now, let us know.

01:52Data science means there are three major components.

01:55One is pre-processing.

01:57One is action.

01:59One is post-processing.

02:01This analogy means that

02:02the juice will be ready.

02:04The machine will be ready.

02:06The machine will be ready.

02:08The juice will be ready.

02:10The machine will be ready.

02:12The machine will be used as data science.

02:16The method is confirmed.

02:17The machine will be complete.

02:20The machine will be prepared.

02:21The machine will� lang to perform.

02:25The machine will make the exact ось.

02:26The machine will actually affect based on data.

02:28It begins for data to

02:32It is a pre-processing field in itself, you can hear a term frequently and it is called data engineering.

02:46This is a field in itself.

02:51So first you have to clear data, because data is basically not clean, it is not ready for action.

03:04Second, you have to perform action on it.

03:06You have to perform data on your customer.

03:08You have to say that it is housing sales.

03:11You have to tell me if it is a 5-plus-plus-plus-plus-plus-plus-plus-plus-plus-plus-plus-plus-plus-plus-plus.

03:17Basically, you have to perform action on a algorithm, which will give you results.

03:21Then one thing is action.

03:24Then you have to do the results, you have to do the results.

03:28That will be post-processing.

03:30Now the actual work, the actual results will be made in action.

03:37Action is performed basically by machine learning.

03:40Machine learning has different types of different types.

03:44Machine learning has three types.

03:47One is supervised learning, one is unsupervised, and one is reinforced learning.

03:51Now let's go back to the next slide.

03:54Machine learning has two types of learning.

03:57One is machine, one is learning.

03:59A machine is learning.

04:01One is machine, one is learning.

04:04If you have to ask machine learning by definition,

04:07definition

04:09to predict

04:11something

04:13machine learning

04:15learn

04:17predict

04:19simple as this

04:21data

04:23now

04:25this

04:27one way or the other

04:31value

04:33predict

04:35machine learning

04:37definition

04:39ml is equal to

04:41lp

04:43machine learning

04:45basic types

04:47supervised learning

04:49unsupervised

04:51reinforced

04:53you

04:55ignore

04:57now

04:59now

05:01you

05:03know

05:05you

05:07know

05:09you

05:11know

05:13you

05:15know

05:17you

05:19know

05:21data

05:23now

05:25data

05:27labeled

05:29data

05:31labeled

05:33data

05:35unlabeled

05:37data

05:39unlabeled

05:40data

05:41labeled

05:43unlabeled

05:44good

05:45supervised

05:46machine learning

05:47you

05:49label data

05:51you

05:52can

05:53tell you

05:54this

05:55spreadsheet

05:56is

05:5710

05:58column

05:59in

06:00motor

06:01bikes

06:02so

06:04you

06:05can

06:06do

06:08this

06:10classification

06:12this

06:14classification

06:16is

06:18supervised

06:19learning

06:20this

06:21car

06:22here

06:23car

06:24here

06:25bike

06:26here

06:27bike

06:28here

06:29basically

06:31classify

06:32this

06:33area

06:34this

06:35bike

06:36is

06:37classification

06:38classification

06:39classification

06:40classification

06:41basically

06:42supervised learning

06:43sub-categories

06:44classification

06:45classification

06:46is

06:47predictive

06:48measure

06:49regression

06:50for example

06:51these

06:52price

06:53values

06:54are

06:55so

06:56simple

06:57simple

06:58machine

06:59learning

07:00which

07:01is

07:02predictive

07:03measure

07:04this

07:05is

07:06regression

07:07how

07:08regression

07:09how

07:10it

07:11was

07:12supervised

07:13learning

07:14which

07:15you

07:16gave

07:17data

07:18and

07:19you

07:20give

07:21task

07:22and

07:23you

07:24classify

07:25or

07:26this

07:27next

07:28value

07:29so

07:30what

07:31did

07:32data

07:33and

07:34task

07:35and

07:36expected

07:37results

07:38excellent

07:39the

07:40unsupervised

07:41learning

07:42unsupervised

07:43data

07:44is

07:45unlabeled

07:46data

07:47and

07:48you

07:49see

07:50columns

07:51but

07:52you

07:53don't know

07:54it

07:56it

07:57it

07:58doesn't

07:59know

08:00you

08:01can

08:02do

08:03you

08:04think

08:05it

08:06is

08:07it

08:08you

08:09can

08:10do

08:11you

08:12do

08:13you

08:14do

08:15do

08:16classification what will be, or regression what will be.

08:19You understand me about it.

08:20So now what do you need to do?

08:22You say that you have to take the data,

08:24but you don't give a task.

08:26You have to take the result yourself.

08:28What do you need to do?

08:30This is basically a type of type.

08:32This is basically a type of cluster.

08:34What does machine learning do?

08:36Clustering algorithm do it.

08:38And similar type of object.

08:40It looks like one thing.

08:42It looks like one thing.

08:44It looks like a graph.

08:48And some data values.

08:50Let's say, some values here.

08:52Some values here.

08:54Some values here.

08:56Some values here.

08:58This is unlabeled data.

09:00You don't know what it is.

09:02If you say,

09:04you can tell me,

09:06you can tell me,

09:08you can tell me,

09:10you can tell me,

09:12you can tell me,

09:14you can tell me,

09:16you can tell me,

09:18you can tell me,

09:19you can tell me,

09:20you can tell me the data.

09:22It's basically,

09:24you can tell me,

09:26these things are placed on the data.

09:28It's basically,

09:30unsupervised learning.

09:32We can reinforce learning.

09:36We can reinforce learning.

09:38We can do data again.

09:40But again, this time, you can do task.

09:45You can do task.

09:46You can set of rules.

09:48Set of rules.

09:50For example, Google has AlphaGo.

09:54Google has AlphaGo.

09:57It's a big champion.

10:03It's an intuition.

10:05You can tell us about rules.

10:08If you play a rules, you can play a rules.

10:10You can play rules.

10:12You can play rules.

10:14You can play a game.

10:16You can play a game.

10:18You can play a game.

10:20You can play a game.

10:22You can play rules.

10:24Now, outcome, task.

10:26You can play a game.

10:27If you play a game, in this case, you can play out.

10:33If you play a game, you can play out.

10:34You can play a game on a child.

10:36You are basically learning.

10:37If you take a 법, you don't have data.

10:39I have data.

10:40I don't do task.

10:41I will set of rules.

10:42And the job will be right.

10:43I will reward you.

10:44And the job will be wrong.

10:46Now, the job is doing results.

10:48You can play better on a result.

10:50So, this one will grow the results again.

10:52The work will be multiple times.

10:53This game will be played.

10:55games in the game. So if you can see these three things, you can see this whole landscape.

11:04This whole thing is called Artificial Intelligence, AI. How does it feel?

11:16See you in the next one.

Category

Transcript

Recommended