Introduction to Artificial Intelligence

Dr. Ram Prasad Padhy, Dept. of CSE, IIITDM Kancheepuram

Human CognitionAbilities

LEFT BRAIN FUNCTIONS RIGHTBRAIN FUNCTIONS

Logic Creativity
Analysis Imagination
Sequencing Holistic Thinking
Mathematics Intuition
Language Arts (Motor Skill)
Facts Rhythm(beats)
Words of Visualization
songs Tune of songs
Computation Daydreaming

Modern AI is the
Symbolic methods: ClassicalAI Statistical methods: ML
convergence of these two

2
What is Intelligence?

Reasoning Learning

Knowledge Communication

Planning Perception

Kinesthetic
 What is “Artificial Intelligence”?

Turing Test (1950)

• The computer is interrogated by a human via
a teletype.
• It passes if the human cannot tell if there is a
computer or human at the other end

4
IIT KHARAGPUR
Evolution of AI

1956 1980 1997 2011 2012 2015 2016

1950 1969 1987-1993 2008 2011/12 2014 2016 2018

Kasparov versus Deep Blue

On May 11, 1997, it won a 6-game

match by 2 wins to 1 with 3 draws

Today, we have power to evaluate

200 million moves per second !!
What are the green fields for AI in India?

• Preventive and affordable Healthcare

• Agriculture and Rural Development
• Smart Mobility and Intelligent Transportation Systems
• Retail
• Manufacturing
• Energy management
• Smart Cities
• Education and Skilling

Source: NitiAayog Discussion Paper onAI, June 2018

Artificial Intelligence

CORE CAPABILITIES
• The ability to solve problems
• Constraint satisfaction, Optimization,
Search
• The ability to plan
• Abstraction
• The ability to deduce
• Logic, Reasoning algorithms
• The ability to learn
• Models, Data, Learning algorithms
• The ability to handle uncertainty
• The ability to interface with the real world

Source:Accenture
Constraints and Optimization

Path Finding
• I wish to find a shortest path
• I wish to find a path with minimumcongestion
• I wish to find a path with combination of transportation
options(metro, bus, taxi)
• I wish to find a path whichgoes past a medicineshop
• I wish to find a path whichminimizes energy
consumption frommybattery in a e-vehicle
When the size and complexity becomes too big we use
“heuristic functions” to cut out unnecessary parts.

In the lack of domain knowledge, wecan statistically learn

the best way (reinforcement learning) by exploration.

ModernAI aims to combine learning from data with

structured use of domain knowledge.

9
 AI Planning
Elements of a Planning Problem
• Aset of states (worlds) described in terms of predicates
• Aset of actions which transforms some parts of one world to
take us to another world
• An initial world
• Agoal in terms of the predicates that must hold in the final
world

Planning is widely used in robotics and automated control

ModernAI explores techniques that combine planning with

machine learning
• Autonomous driving is one of many areas where such
combinations are highly relevant

10
 Logical Reasoning
• Automated ways to use what is known to reason
about something which is not explicitly known.
• Automated Reasoning:
• Deduction
Rule: All the marbles in this bag are blue
Case: These marbles are fromthis bag
Inference: These marbles are blue
Five color theorem: All mapscanbecoloredwith five
colors, where neighboring countries get different colors
• Abduction [Proved in 1800s]
Rule: All the marbles in this bag are blue
Fourcolor theorem: All mapscanbecoloredwith four
Observation: These marbles are blue colors, where neighboring countries get different colors
Case: These marbles are fromthis bag [Proved in 1976 with help of computers]

• Induction Applications of Logical Reasoning

Case: These marbles are fromthis bag • Automated TheoremProving
• Rule-based Systems
Observation: These marbles are blue • ComplexityAnalysis
Rule: All the marbles in this bag are blue
 Logical Reasoning with Other Fun Things

father( x, z ), father( z, y ) Whois the maternal great uncle of Freya?

 grandfather( x, y )

father( x, z ), mother( z, y )
 maternalgrandfather( x, y )

mother( x, z ), mother( z, y )
 maternalgrandmother( x, y )

mother( x, z ), mother( z, y )
 grandmother( x, y )

maternalgrandmother( x, z ),
mother( z, p ), son( p, y )
 maternalgreatuncle( x, y )
maternalgrandmother( Freya, Charlotte ),
mother( Charlotte, Lindsey ), son( Lindsey, Fergus )
 maternalgreatuncle( Freya, Fergus )

Wecould build this into a social media platform which suggests Freya to post a picture of Fergus on
the Maternal-Great-Uncle day !!
12
 Reasoning under Uncertainty
P(Obesity)
0.24 History of History of viral Histo P(Chron
Obesity
alcohol abuse hepatitis ry of ic
VH Hepatitis)
T 0.3
Hepatitic steatosis Cirrhosis Chronic Hepatitis F 0.05

Triglycerides AST ALT Total bilirubin Fatigue

AST: Aspartate aminotransferase
ALT:Alanine aminotransferase

Jaundice
• Weknow the relations between events in probabilistic terms
• We are given a set of known events
Challenge: Sometimes we do not know
• Goal: Find the probability of some other event
which is the cause and which is the effect. 13
Machine Learning
Deep Learning and the Problem of Explainability

Test Image Evidence of Husky Evidence of Flute

Husky Classified Explanation Same pixels used to explain two different classifications !!
as Wolf based on
saliency

It has evidence for cat as well as

evidence for bird, but it is neither

…but it is also not easy to define the features that

separate a dogfrom a cat, evenif wecanpaint both
15
The book that we will followmostly for this and
many other topics:

Artificial Intelligence –AModernApproach

Stuart J Russell, Peter Norvig

Pearson Education India

16
• The slides are taken from
https://cse.iitkgp.ac.in/~pallab/artificial_intelligence_autumn_2020/index.html
• The slides are being used only for educational purpose