Vous êtes sur la page 1sur 12

Introduction to Artificial Intelligence

Lecture-01

Hema Kashyap
Basic Concept of AI

 Concerned with the design of intelligence in artificial device.


 Term was coined by McCarthy in 1956.
 Two ideas in the definition
 Intelligence
 Artificial Device
What is Intelligence

 As Human
 Ideal Performance

 Thought Process /Reasoning


 Final Manifestation in terms of its Actions
What’s involved in Intelligence?
• Ability to interact with the real world
▫ to perceive, understand, and act
▫ e.g., speech recognition and understanding and synthesis
▫ e.g., image understanding
▫ e.g., ability to take actions, have an effect

• Reasoning and Planning


▫ modeling the external world, given input
▫ solving new problems, planning, and making decisions
▫ ability to deal with unexpected problems, uncertainties

• Learning and Adaptation


▫ we are continuously learning and adapting
▫ our internal models are always being “updated”
 e.g., a baby learning to categorize and recognize animals
Defining Artificial Intelligence
 Definition vary along two dimensions
Thought and Reasoning
System that think
System that Thinks Rationally
like Human Eg: Laws of
Eg: Cognitive Thoughts and
Human like Modeling Logic Ideal Performance
Performance /Rationality
System That act System that act
like Human Rationally
Eg: Turing Test Eg: Rational Agent

Behavior/Actions
Thinks Humanly: The Cognitive
modeling approach

 It talks about a program that thinks like human


 There are two ways to do so:
 Introspection
 Through Psychological Experiments
 Eg: Program that plays chess like human
Think Rationally: The “Laws of
Thought” process
 A Greek philosopher Aristotle was the first one to codify “Right Thinking” i.e.
reasoning process.
 His syllogism provided patterns for arguments structures that always yielded
correct solutions/conclusions when given correct premises
 Eg:
 Socrates is a man.
 All men are mortal.
 Therefore, Socrates is mortal.
 This study initiated the field called Logic
 Two obstacles to this approach:
 State problem in the formal terms using logical notations
 There’s a difference between being able to solve a problem “in principle” and
implementing it in real.
Acting Humanly: The Turing Test
Approach
 Proposed by Alan Turing in 1950 to provide a satisfactory
definition of AI.
 He suggested a test based on in-linguiability from
undeniably intelligent entity-human beings.
 The computer passes the test if a human interrogator ,
posing the written questions, cannot tell whether the
responses came from a person or not.
 But to achieve this a computer would need to possess
following capabilities:
 Natural Language Processing
 Knowledge representation
 Automated Reasoning
 Machine Learning
Total Turing Test

 This test includes the video signal so that the


interrogator can test the subject’s perception
abilities.
 To pass this computer needs
 Computer Vision: to perceive objects
 Robotics: to manipulate objects and move about.
Chinese Room Test
 Room with operator and huge
Chinese literature
 Chinese people outside sending in
some Chinese texts.
 If the operators on looking up the
literature able to respond /send text
written in front of the text received,
then person outside believes
operator knows Chinese.
 Its just the matter of “Translating”.
 This doesn’t mean that the person
understands semantics of the
language.
 So, Cognition and Understanding is
different thing
Acting Rationally: The Rational agent
Approach
 Agent(that acts), and a computer program agent is more than just a mere
program, the one
 That operates under autonomous control
 Perceive their environment
 Persisting over a prolonged time period
 Adapting for change
 Being capable of taking an another’s goal
 A Rational Agent is the one that acts so as to achieve the best outcome or when
there is uncertainty, the best expected outcome.

 Act Rationally Reason Logically Draws Conclusions

Acts on that conclusion


Defining: Typical AI problem

 Intelligent Agents need to be able to do both


“MUNDANE” and “EXPERT” task.

 Mundane Task: planning route actively, recognizing,


communicating etc.

 Expert Task(needs domain specific knowledge):


medical diagnosis, mathematical problem solving etc.

Vous aimerez peut-être aussi