JOMO KENYATTA UNIVERSITY OF AGRICULTURE

AND TECHNOLOGY (JKUAT)

DEGREE FOR BACHELOR OF SCIENCE IN

INFORMATION TECHNOLOGY

YEAR THREE SEMSETER TWO

NAME: YEL DANIEL DENG

REG NO: SC221-0586/2016

UNIT CODE: BIT 2319

UNIT TITLE: ARTIFICIAL INTELLIGENCE

Assignment one
1. Comment on the eligibility of Turing’s test for computer intelligence, and his belief that
computers with 109 bits of storage would pass a 5-minute version of his test with 70%
probability.

 The Turing test is a test of a machine’s ability exhibit intelligence behavior to, or
indistinguishable from that of a human. The Turing test was developed by Alan Turing in
1950.

 He published his test of computer intelligence, referred to as Turing test. The test
consisted of a person asking questions via a keyboard to both a person and a keyboard.

 Alan Turing believed that machines could be created that would mimic the processes of
the human brain. Turing strongly believed that there was nothing the brain could do
that a well-designed computer could not.

 The Turing proposed that a human evaluator would judge natural languages
conversations between a human and a machine designed to generate human-like
responses.

 Since Turing first introduced his test, it has proven to be both highly influential and
widely criticized, and it has become an importance concept in the philosophy of artificial
intelligence.

2. Comment on the eligibility of the definition of artificial intelligence as given by the 1996
IEEE Neural Networks Council.
 Artificial Intelligence is the study of how to make computers do things at which people
are doing better. Artificial Intelligence is a branch of computer science that aims to
create intelligence machines.

 Artificial Intelligence was designed to handle the activities such as speech recognition,
learning, planning, and problem solving.

 Artificial Intelligence has as a subset known as Computational Intelligence.

Computational Intelligence refers to the ability of a computer to learn a specific task
from data or experimental observation.

 Artificial neural networks were inspired from brain modeling studies. Neural network is
a tangible system with very strong pattern recognition capabilities.
 3. Based on the definition of CI given in this chapter, show that each of the paradigms (NN, EC, SI,
AIS, and FS) does satisfy the definition.
 Computational Intelligence refers to the ability of a computer to learn a specific task
from data or experimental observation.

Computational Intelligence paradigms.

AIS

NN EC

FS SI

Probabilistic Techniques

i. Artificial Neural Networks (NN):

 The brain is a complex, nonlinear and parallel computer. Neural network is a tangible
system with very strong pattern recognition capabilities.
It has the ability to perform tasks such as:
o Pattern recognition
o Perception
o And motor control much faster than any computer.

 An artificial neural network (NNs) is a layered network of Ans. An NN may consist of an:
o Input layer
o Output layer
 o Hidden layers
Hidden layer

Input layer

Output
layer

ANs in one layer are connected, fully or partially to the ANs in the next layer. Feedback
connections to previous layers are also possible.

ii. Evolutionary computation (EC):

 Applies biologically inspired concepts such as population, mutation and survival of the
fittest to generate increasingly better solutions to the problem.

 These methods most notably divide into evolutionary algorithms (e.g. genetic
algorithms) and swarm intelligence.

 Evolutionary algorithms use a population of individuals, where an individual is referred

to as a chromosome. A chromosome defines the characteristics of individuals in
the population.

 Evolutionary computation (EC) has as its objective to mimic processes from natural
evolution, where the main concept is survival of the fittest

iii. Artificial immune systems (AIS):

 The neural immune system has an amazing pattern matching ability, used to distinguish
between foreign cells entering the body and the cells belonging to the body.

 An artificial immune system (AIS) models some of the aspects of a NIS, and is mainly
 applied to solve pattern recognition problems, to perform classification tasks, and to
cluster data.
iv. Swarm intelligence (SI):
 Swarm Intelligence generated from the study of colonies, or swarms of social organisms.
Studies of the social behavior of organisms in swarms prompted the design of very
efficient optimization and clustering algorithms.

 Studies of the social behavior of organisms (individuals) in swarms prompted

the design of very efficient optimization and clustering algorithms.

 Particle swarm optimization (PSO) is a stochastic optimization approach, modeled on

the social behavior of bird flocks.

v. Fuzzy Systems (FS):

 Fuzzy system is a technique for reasoning under uncertainty. It has been widely used in
modern industrial and consumer product control systems. Fuzzy sets and fuzzy logic
allow what is referred to as approximated reasoning.

 Fuzzy systems have been applied successfully to control systems, gear transmission ant
braking systems in vehicles, controlling lifts etc.

 The uncertainty in fuzzy systems is referred to as nonstatistical uncertainty, and should

no be confused with statistical uncertainty.

 Statistical uncertainty is based on the law of probability; whereas nonstatistical

uncertainty is based on vagueness, imprecision and/ or ambiguity.