ARTIFICIAL

INTELLIGENCE
1
Rahul Sachdeva
 INTRODUCTION
Course Objective:
▪ Introduce the basic concepts of artificial intelligence, problem-solving,
knowledge representation and reasoning.
▪ Learn the basic concepts of handling uncertainty
▪ Help the students to applications of AI in different fields

2
 INTRODUCTION
▪ Course Outcome: Upon successful completion of the course, students will be
able to:

▪ CO1: Learn the different concepts and strategies of Artificial Intelligence.

▪ CO2: Recognize various representations techniques for knowledge
extraction using different tools.
▪ CO3: Apply concepts of decision making for handling uncertainty in various
applications.
▪ CO4: Implement different strategies of artificial intelligence for solving real
world problems.

3
SYLLABUS
UNIT - I
Introduction to AI: Brief introduction about Intelligent agents and Problem Solving.
Turing Test. Uninformed Search Strategies, Informed Search Strategies, Heuristics.
Solving problems by searching, BFS, DFS, Issues in design of Intelligent Search
Algorithms.
UNIT - II
Knowledge Representation: Knowledge Representation using predicate logic, Rule
Based Systems, Ontology, WordNet and Concept Net as Knowledge representation
tools. Programming with Prolog/Lisp. Text Feature Extraction - BoW Model, TF-IDF.
Word Embeddings - Word2Vec, GloVe.

4
SYLLABUS
UNIT - III
Decision Making in Uncertainty: Handling Uncertainty, Probabilistic Reasoning, Fuzzy
Logic, Learning by induction, Introduction to Neural Network Genetic Algorithms basics.
Rough Sets. Case Studies of Applications of Uncertainty
UNIT - IV
Real World Applications of AI: Real World Applications of AI: Expert System
Architecture, Case Studies: MYCIN, Applications in NLP, Medical Sciences, Social Network
Analysis, Information Retrieval from Search Engines and Metasearch Engines, IoT
Applications & Big Data Analytics Applications. Ethics in AI.

5
BOOKS TO REFER
▪ S.J. Russell and P. Norvig, “Artificial Intelligence- A
Modern Approach”
▪ P.H. Winston, “Artificial Intelligence”, Pearson
Education

6
WHAT IS INTELLIGENCE?
▪ The exact definition of intelligence is complex and controversial.
Psychologists have debated over an exact definition for years.
▪ One could certainly define intelligence by the properties one
exhibits, for instance the ability to:
▪ deal with new situation,
▪ solve problems,
▪ answer questions,
▪ devise plans, and so on.

7
INTELLIGENCE OR INTELLIGENT BEHAVIOR CAN ALSO
BE DEFINED IN TERMS OF ONE’S CAPACITY FOR:
▪ Abstract thinking,
▪ Self-awareness,
▪ Communication,
▪ Learning and understanding from experiences
▪ Memory and Planning,
▪ Creativity and problem solving.
▪ Making sense out of ambiguous and contradictory messages
▪ Responding effectively to and dealing with complex situations
▪ Applying knowledge to manipulate the environment
▪ Intelligence does not necessarily mean how fast information is processed,
but it is the ability to demonstrate intelligence by communicating effectively
(by any means) and by learning new concepts (by any means). 8
ARTIFICIAL INTELLIGENCE: DEFINITION
▪ Simulation of Intelligence in machines.

▪ It is the science and engineering of making intelligent machines,

especially intelligent computer programs.

▪ Artificial intelligence is the study of systems that act in a way that to

any observer would appear to be intelligent.

▪ It is related to the similar task of using computers to understand human

intelligence, but AI does not have to confine itself to methods that are
biologically observable.
9
ARTIFICIAL INTELLIGENCE
▪ AI is a collection of hard problems which can be solved by humans and
other living things, but for which we don’t have good algorithms for solving.
▪ e. g., understanding spoken natural language, medical diagnosis, circuit
design, learning, self-adaptation, reasoning, game playing, etc.

• A computer program that

▪ Acts like human (Turing test)
▪ Thinks like human (human-like patterns of thinking steps)
▪ Acts or thinks rationally (logically, correctly)

• The art of creating machines that perform functions that require intelligence
when performed by humans.
10
STRONG & WEAK AI
▪ Weak AI, an artificial intelligence system which is only intended to be
applicable on a specific kind of problem (e.g. computer chess) and
not intended to display human-like intelligence in general.

▪ Siri is a good example of narrow intelligence. Siri operates within a

limited pre-defined range, there is no genuine intelligence, no self-
awareness, no life despite being a sophisticated example of weak AI.

11
STRONG AND WEAK AI
▪ Strong AI is the intelligence of a machine that can successfully perform any
intellectual task that a human being can. It is a primary goal of artificial
intelligence research and an important topic for science fiction writers and
futurists.
▪ Strong AI also refers to as "full AI" or as the ability to perform "general
intelligent action "
▪ The followers of strong AI believe that by giving a computer program
sufficient processing power, and by providing it with enough intelligence,
one can create a computer that can literally think and is conscious in the
same way that a human is conscious.
- The Turing Test (Turing) - The Robot College Student Test (Goertzel)
- The Coffee Test (Goertzel) - The Employment Test (Nilsson)

12
 ARTIFICIAL
VS
NATURAL INTELLIGENCE

13
ADVANTAGES OF ARTIFICIAL INTELLIGENCE:
▪ AI is more permanent. AI is permanent as long as the computer systems or
programs remain unchanged.

▪ AI offers ease of duplication and distribution. Transferring a body of knowledge

from one person to another usually requires a lengthy process, yet fully expertise
can never be transfer. However, knowledge embodied in computer systems can be
copied or duplicated to another and so on.

▪ AI can be less expensive that natural intelligence. Some times buying computer
software costs less than having corresponding human power to carry out same task.

▪ AI can be documented. Decisions made by a computer can be easily documented

by tracing the activities of a system, while natural intelligence is difficult to trace out.

14
ADVANTAGES OF NATURAL INTELLIGENCE:
▪ Natural Intelligence is creative, while AI is uninspired. The ability to acquire
knowledge is inherent in human mind, but with AI customized knowledge must
be built into a carefully constructed system.
▪ Natural intelligence enables people to benefit from and use sensory
experience directly, while AI mostly works on symbolic inputs.
▪ Natural intelligence is able to make reasons at all times by wide context of
experience and bring it to bear on individual problems. While AI systems
typically gain their power of knowledge by having a narrow focus of problem
domain.
▪ Natural Intelligence is powerful but has limitations. Humans are intellectual
but have limited knowledge bases, and information processing is comparably
slow in brain when done with computers.

15
WHAT IS AI?
Systems that think like Systems that think
humans rationally

Systems that act like Systems that act

humans rationally
HOW AI WORKS:
▪ Think well

▪ Act well

▪ Think like humans

▪ Act like humans

17
THINK WELL
▪ Develop formal models of knowledge
representation, reasoning, learning, memory,
problem solving that can be rendered in algorithms.

▪ There is often an emphasis on systems that are

provably correct, and guarantee finding an optimal
solution.

18
ACT WELL
▪ For a given set of inputs, generate an appropriate output that is not
necessarily correct but gets the job done.

▪ A heuristic (heuristic rule, heuristic method) is a rule of thumb,

strategy, trick, simplification, or any other kind of device which
drastically limits search for solutions in large problem spaces.

19
ACT WELL
▪ Heuristics do not guarantee optimal solutions; in fact, they do not
guarantee any solution at all: all that can be said for a useful
heuristic is that it offers solutions which are good enough most
of the time.

20
THINK LIKE HUMANS
▪ Cognitive science approach

▪ Focus not just on behavior and I/O but also look at reasoning process.

▪ Computational model should reflect “how” results were obtained.

▪ Provide a new language for expressing cognitive theories and new

mechanisms for evaluating them

21
THINK LIKE HUMANS
▪ GPS (General Problem Solver): Goal not just to produce humanlike
behavior, but to produce a sequence of steps of the reasoning
process that was similar to the steps followed by a person in solving
the same task.

▪ ELIZA: A program that simulated a psychotherapist interacting with a

patient and successfully passed the Turing Test.

22
ACT LIKE HUMANS
▪ Behaviorist approach.

▪ Not interested in how you get results, just the similarity to what human
results are.

▪ Exemplified by the Turing Test (Alan Turing, 1950).

23
TURING TEST
▪ Three rooms contain a person, a computer,
and an interrogator.
▪ The interrogator can communicate with
the other two.
▪ The interrogator tries to determine which
the person is and which the machine is.
▪ The machine tries to fool the interrogator
into believing that it is the person.
▪ If the machine succeeds, then we conclude
that the machine can think.

24
ACTING HUMANLY: THE TURING TEST
Turing (1950) “Computing machinery and intelligence”:
♦ “Can machines think?” −→ “Can machines behave intelligently?”
♦ Operational test for intelligent behavior: the Imitation Game

HUMAN

HUMAN
INTERROGATOR ?
AI SYSTEM

♦ Predicted that by 2000, a machine might have a 30% chance of fooling a lay person for
5 minutes
♦ Anticipated all major arguments against AI in following 50 years
♦ Suggested major components of AI: knowledge, reasoning, language understanding, learning
Problem: Turing test is not reproducible, constructive, or amenable to
mathematical analysis
 AI APPLICATION AREAS
▪ Game Playing
▪ Automated Reasoning
▪ Theorem Proving
▪ Natural Language Processing
▪ Expert Systems
▪ Computer Vision
▪ Robotics
▪ Machine Learning

26
PRACTICAL AI TOOLS USED NOWADAYS
On your phone:
▪ Siri: Part of Apple’s iOS, watchOS, and tvOS. Intelligent personal
assistant.
▪ Google Now: Available within Google Search mobile app for Android
and iOS as well as the Google Chrome web browser on other
devices. Delegates requests to web services powered by Google.

27
28
THANK YOU

Any QUESTIONS?