TMLAI-11195.pdf

Page 1 of 6

Transactions on Machine Learning and Artificial Intelligence - Vol. 9, No. 6

Publication Date: December, 25, 2021

DOI:10.14738/tmlai.96.11195. Gajawada, S., & Mustafa, H. M. H. (2021). The Interesting and Complete Artificial Intelligence (ICAI) – Version 1. Transactions on

Machine Learning and Artificial Intelligence, 9(6). 20-25.

Services for Science and Education – United Kingdom

The Interesting and Complete Artificial Intelligence (ICAI) –

Version 1

Satish Gajawada

IIT Roorkee Alumnus

Hassan M. H. Mustafa

Banha University

ABSTRACT

A new field titled “The Interesting and Complete Artificial Intelligence (ICAI)” is

invented in this work. In this article, we define this new ICAI field. Four new ICAI

algorithms are designed in this work. This paper titled “The Interesting and

Complete Artificial Intelligence (ICAI) – Version 1” is just the starting point of this

new field. We request Research Scientists across the globe to work in this new

direction of Artificial Intelligence and publish their work with titles such as “The

Interesting and Complete Artificial Intelligence (ICAI) – Version 1.1”, “The

Interesting and Complete Artificial Intelligence (ICAI) – Version 2” or “The

Interesting and Complete Artificial Intelligence (ICAI) – Final Version”.

Keywords: Interesting, Complete, Interesting and Complete Artificial Intelligence,

Artificial Intelligence, AI, ICAI

DEFINITION OF THE INTERESTING AND COMPLETE ARTIFICIAL INTELLIGENCE FIELD

In this work we took inspiration from “Friendship”, “Brotherhood”, “Mother and Son” and

“Husband and Wife” and designed four new algorithms. The goal of this project is that the

concepts like “Friendship”, “Brotherhood”, “Mother and Son” and “Husband and Wife” would

make the current Artificial Intelligence Interesting and Complete. Hence we have defined this

new field with title “The Interesting and Complete Artificial Intelligence (ICAI)” as below:

All the Artificial Intelligence Algorithms (AI Algorithms) which are inspired from

“Friendship”, “Brotherhood”, “Mother and Son” and “Husband and Wife” will

become part of new field titled “The Interesting and Complete Artificial Intelligence

(ICAI)”.

LITERATURE REVIEW

There are no “The Interesting and Complete Artificial Intelligence (ICAI)” field algorithms

designed in literature till date. The World’s First ICAI algorithm is designed in this project. For

the sake of completeness, we are showing Artificial Intelligence Literature [1] to [25] from

previous article of Satish Gajawada et al titled “Ten Artificial Human Optimization Algorithms”

published at “Transactions on Machine Learning and Artificial Intelligence, United Kingdom”.

ARTIFICIAL FRIENDSHIP ALGORITHM

Artificial Friendship Algorithm is based on two friends “Friend One” and “Friend Two”. Based

on random number generated in line number 6 and FriendOneProbabaility the person is

Page 2 of 6

Gajawada, S., & Mustafa, H. M. H. (2021). The Interesting and Complete Artificial Intelligence (ICAI) – Version 1. Transactions on Machine Learning

and Artificial Intelligence, 9(6). 20-25.

URL: http://dx.doi.org/10.14738/tmlai.96.11195.

identified as Friend One or Friend Two. Friend One is strong and hence always updates position

and velocity irrespective of anything. Friend Two is weak. Based on random number generated

and HelpOfFriendOneProbability in line number 10 the Friend Two either receives help from

Friend One or not. Friend Two moves in search space and updates position and velocity when

he receives help from Friend One. Friend Two without help from Friend One is halted and does

nothing. Figure 1 shows Artificial Friendship Algorithm.

1) All Artificial Friend Ones and Artificial Friend Twos are initialized

2) Iterations count is set to zero

3) Identify local best of all Artificial Friend Ones and Artificial Friend Twos

4) Identify global best of all Artificial Friend Ones and Artificial Friend Twos

5) for each particle i do

6) if ( generate_random_number (0,1) < FriendOneProbability ) then // Friend One

7) Update Velocity of Artificial Friend One

8) Update Position of Artificial Friend One

9) else // Friend Two

10) if ( random(0,1) < HelpOfFriendOneProbability) then // Friend Two with

Help

11) Update Velocity of Friend Two

12) Update Position of Friend Two

13) else // Friend Two without help does nothing

14)

15) end if

16) end if

17) end for

18) generations (iterations) = generations (iterations) + 1

19) while ( termination_condition not reached is true)

Figure 1. Artificial Friendship Algorithm

ARTIFICIAL BROTHERHOOD ALGORITHM

Artificial Brotherhood Algorithm is based on two brothers “Brother One” and “Brother Two”.

Based on random number generated in line number 6 and BrotherOneProbabaility the person

is identified as Brother One or Brother Two. Brother One is strong and hence always updates

position and velocity irrespective of anything. Brother Two is weak. Based on random number

generated and HelpOfBrotherOneProbability in line number 10 the Brother Two either receives

help from Brother One or not. Brother Two moves in search space and updates position and

velocity when he receives help from Brother One. Brother Two without help from Brother One

is halted and does nothing. Figure 2 shows Artificial Brotherhood Algorithm.

1) All Artificial Brother Ones and Artificial Brother Twos are initialized

2) Iterations count is set to zero

3) Identify local best of all Artificial Brother Ones and Artificial Brother Twos

4) Identify global best of all Artificial Brother Ones and Artificial Brother Twos

5) for each particle i do

6) if ( generate_random_number (0,1) < BrotherOneProbability ) then // Brother

One

7) Update Velocity of Artificial Brother One

Page 3 of 6

Transactions on Machine Learning and Artificial Intelligence (TMLAI) Vol 9, Issue 6, December - 2021

Services for Science and Education – United Kingdom

8) Update Position of Artificial Brother One

9) else // Brother Two

10) if ( random(0,1) < HelpOfBrotherOneProbability) then // Brother Two

with Help

11) Update Velocity of Brother Two

12) Update Position of Brother Two

13) else // Brother Two without help does nothing

14)

15) end if

16) end if

17) end for

18) generations (iterations) = generations (iterations) + 1

19) while ( termination_condition not reached is true)

Figure 2. Artificial Brotherhood Algorithm

ARTIFICIAL MOTHER AND SON ALGORITHM

Artificial Mother and Son Algorithm is based on “Mother” and “Son”. Based on random number

generated in line number 6 and MotherProbability the person is identified as Mother or Son.

Mother is strong and hence always updates position and velocity irrespective of anything. Son

is weak. Based on random number generated and HelpOfMotherProbability in line number 10

the Son either receives help from Mother or not. Son moves in search space and updates

position and velocity when he receives help from Mother. Son without help from Mother is

halted and does nothing. Figure 3 shows Artificial Mother and Son Algorithm.

1) All Artificial Mothers and Artificial Sons are initialized

2) Iterations count is set to zero

3) Identify local best of all Artificial Mothers and Artificial Sons

4) Identify global best of all Artificial Mothers and Artificial Sons

5) for each particle i do

6) if ( generate_random_number (0,1) < MotherProbability ) then // Mother

7) Update Velocity of Artificial Mother

8) Update Position of Artificial Mother

9) else // Son

10) if ( random(0,1) < HelpOfMotherProbability) then // Son with Help

11) Update Velocity of Son

12) Update Position of Son

13) else // Son without help does nothing

14)

15) end if

16) end if

17) end for

18) generations (iterations) = generations (iterations) + 1

19) while ( termination_condition not reached is true)

Figure 3. Artificial Mother and Son Algorithm