1
00:00:00,330 --> 00:00:07,770
Hello and welcome to this lecture, where you are going to learn the differences between evolutionary

2
00:00:07,770 --> 00:00:11,220
algorithms and genetic algorithms.

3
00:00:11,610 --> 00:00:19,530
These are two very common terms in this area, and they are often confused as if they were the same.

4
00:00:19,890 --> 00:00:23,820
However, there is a small difference between them.

5
00:00:24,090 --> 00:00:26,610
That is very important, you know?

6
00:00:27,060 --> 00:00:30,930
Now let's quickly look at some definitions.

7
00:00:31,500 --> 00:00:40,830
First, we have the category of evolutionary algorithms, which is composed of computational models

8
00:00:40,830 --> 00:00:45,270
that represent the natural processes of evolution.

9
00:00:45,480 --> 00:00:53,370
This simulation of species, the survival of the fittest, are the best individual.

10
00:00:53,370 --> 00:01:02,830
And also there are some other areas that are related to self-organization and adaptive behavior.

11
00:01:02,910 --> 00:01:13,020
It is important to emphasize that these algorithms are part of a large in Marica area than genetic algorithms,

12
00:01:13,440 --> 00:01:17,340
as if it were the root of the area.

13
00:01:17,700 --> 00:01:24,180
So genetic algorithms are parts of evolutionary algorithms.

14
00:01:24,750 --> 00:01:33,540
As you can read, the here genetic algorithms are a branch of evolutionary algorithms, and the main

15
00:01:33,540 --> 00:01:42,690
idea is who gets bad and bad better solutions through the evolution of previous generations.

16
00:01:43,230 --> 00:01:52,770
Basically, we built an initial generation and apply evolution processes like what happens in the real

17
00:01:52,770 --> 00:01:59,970
world where the new generations are more evolved than past generations.

18
00:02:00,390 --> 00:02:04,980
In short, genetic algorithms are more related.

19
00:02:05,010 --> 00:02:14,100
Should these sand philosophy here, while evolutionary algorithms have more general concepts, this

20
00:02:14,100 --> 00:02:22,810
image shows the entire flow of genetic algorithm that we are going to implement step by step.

21
00:02:22,890 --> 00:02:29,550
First, we create the initial population and then we evaluate it.

22
00:02:29,940 --> 00:02:38,670
Here we have this stop being crit burial, which indicates how long we are going to run the algorithm.

23
00:02:39,060 --> 00:02:47,880
In general, we defined the number of generations that will be created, and we run the algorithm based

24
00:02:47,880 --> 00:02:48,960
on that number.

25
00:02:49,260 --> 00:03:02,400
For example, if we define 100 generations, we will run this entire piece of steps one hundred times.

26
00:03:02,820 --> 00:03:12,930
And the algorithm and so here, when the number of generations equals 100, it is similar to a far loop

27
00:03:12,930 --> 00:03:14,550
in programming languages.

28
00:03:15,180 --> 00:03:24,810
Every time the algorithm will through the diamonds, we construct a new generation and we perform all

29
00:03:24,810 --> 00:03:26,040
these steps.

30
00:03:26,490 --> 00:03:36,970
Select parents crossover mutation, crossover and mutation are called genetic operators.

31
00:03:36,990 --> 00:03:47,040
As you can read here, and the old population is discarded, we then evaluate the new population.

32
00:03:47,550 --> 00:03:57,930
They find this surviving population and return to these in need shows their behavior at the hands of

33
00:03:57,930 --> 00:03:58,860
the process.

34
00:03:59,280 --> 00:04:04,740
We simply list the best individuals are the best solutions.

35
00:04:05,010 --> 00:04:11,550
This lecture was just to show you the general structure of a genetic algorithm.

36
00:04:11,850 --> 00:04:20,070
And don't worry about understanding all the steps now because we are going to analyze and implement

37
00:04:20,100 --> 00:04:23,820
each of them in detail in the next lecture.

38
00:04:24,060 --> 00:04:31,070
You will understand that the problem that we are going to solve and soon after where we started the

39
00:04:31,080 --> 00:04:33,180
implementations, so there.