1 PDF

You might also like

Download as pdf or txt
Download as pdf or txt
You are on page 1of 6

Ai sheet 1 answer

Question 1: Describe briefly:


A) The Turing Test "imitation game". (Illustrate through
drawing)

Answer:
It’s a test made by “Alan Turing” and named after him, it’s an
Operational test for intelligent behavior, and it could be done as
shown in this photo:

So, the test asks that: Can a human interrogator tell whether (written)
responses to his/her questions come from a human or a machine?

What does the AI system need to pass the Turing Test?


o Natural Language Processing
o Knowledge Representation
o Automated Reasoning
o Machine Learning
Minders’21 AC
B) The Total Turing Test:
Answer:
Same as Turing Test but extended to include physical aspects
of human behavior.

What does the AI system need to pass the Total Turing Test?
o Natural Language Processing
o Knowledge Representation
o Automated Reasoning
o Machine Learning
o Computer Vision
o Robotic
Example: Sophia the robot.

C) Systems that “Act/Behave Rationally”, and Systems that


“Act/Behave Humanly”.

Answer:

Systems that “Act/Behave Systems that “Act/Behave


Rationally”: Humanly”:

Minders’21 AC
- An intelligent agent is such that: -Is The study of how to make
computers do things at which, at
the moment, people are better
-Its actions are appropriate for its (Rich and Knight, 1991).
goals and circumstances.

-The art of creating machines that


-It is flexible to changing performs functions that require
environments and goals. intelligence when performed by
people” (Kurzweil, 1990).

-It learns from experience.


-Generally, we can define systems
that “Act/Behave Humanly” as
-It makes appropriate choices following:
given perceptual limitations and
Is to judge the system based on
limited resources bounded
its behavior”.
rationality or bounded optimality.

But why do we want an intelligent


system to act like a human?
-Because for many tasks, humans
are still the Gold Standard.

D) “Weak AI Hypothesis” versus the “Strong AI Hypothesis”.

Minders’21 AC
Answer:

Weak AI Hypothesis Strong AI Hypothesis


- We can accurately simulate - We can create algorithms
animal human intelligence in a that are intelligent
computer. (conscious).

-It do what actually human do


without any change in behavior.
-It can think and learn from
the surrounding
environment by its self.

E) The two most fundamental concerns of AI researchers:

Answer:
The two most fundamental concerns of AI researchers are knowledge
representation and search.
Knowledge representation:
is the field of artificial intelligence (AI) dedicated to representing
information about the world in a form that a computer system can
utilize to solve complex tasks such as diagnosing a medical
condition or having a dialog in a natural language.
Search:

Minders’21 AC
Search techniques are universal problem-solving
methods. Rational agents or Problem-solving agents in AI mostly
used these search strategies or algorithms to solve a specific
problem and provide the best result.

F) Intelligent Agents:

Answer:
An agent is anything that can be viewed as perceiving its
environment through sensors and acting upon that environment
through actuators as shown below:

Question 2: Give the scientific term for each of the following


statements:

a) The branch of computer science that is concerned with the


automation of intelligent behavior.
Minders’21 AC
Answer: (artificial intelligence)

b) A problem-solving technique that systematically explores a space


of problem states.
Answer: (Search).

c) Systems that are constructed by obtaining knowledge from a


human expert and coding it into a form that a computer may
apply to similar problems.
Answer: (Expert systems).
d) Models that parallel the structure of neurons in the human brain
and used to build intelligent programs.
Answer: (Artificial neural network).

e) Algorithms that evolve new problem solutions from components


of previous solutions using specific operators such as crossover
and mutation.
Answer: (Genetic Algorithms).

Minders’21 AC

You might also like