Artificial Intelligence

Introduction

1
 Textbook

 Russell & Norvig: Artificial Intelligence A

Modern Approach (2nd Edition)

“The publication of this textbook was a major step

forward, not only for the teaching of AI, but for the
unified view of the field that this book introduces.
Even for experts in the field, there are important
insights in almost every chapter.” (Amazon.com
review)

(c) 2003 Thomas G. Dietterich and Devika

Subramanian 2
 What is Artificial Intelligence?

 Computer Science
 Methods for applying computers to problems
 Study of the fundamental limits of
computation
 Artificial Intelligence
 Methods for applying computers to problems
that require “intelligence”
 Study of the fundamental limits of
“intelligent” behavior by computers

(c) 2003 Thomas G. Dietterich and Devika

Subramanian 3
(c) 2003 Thomas G. Dietterich and
Devika Subramanian 4
 What is Intelligence?

“Like
“Rationally”
People”

2-
3- Laws of
Think Cognitive
Thought
Science

1-Turing 4- Rational
Act
Test Agents

(c) 2003 Thomas G. Dietterich and Devika

Subramanian 5
(c) 2003 Thomas G. Dietterich and Devika
Subramanian 6
 Act Like Humans:
The Turing Test
 Can Computer fool a human
interrogator?

(c) 2003 Thomas G. Dietterich and Devika

Subramanian 7
 Abilities Required for Turing Test

 Natural Language Processing (understanding,

generation)
 Automated Reasoning
 Learning
 Knowledge Representation and Storage
 Vision (for “total turing test”)
 Robotics (for “total turing test”)

Problem: Tends to focus on human-like errors,

linguistic tricks, etc. Does not product useful
computer programs
(c) 2003 Thomas G. Dietterich and Devika
Subramanian 8
Think Like Humans:
Cognitive Science

(c) 2003 Thomas G. Dietterich and Devika

Subramanian 9
 Ensure that all actions performed by computer are
justifiable (“rational”)

Facts and Rules

Theorem Prover
in Formal Logic

 Rational = Conclusions are provable from inputs and

prior knowledge
 Problems:

Representation of informal knowledge is difficulty

Hard to define “provable” plausible reasoning

Combinatorial explosion: Not enough time or space to prove
desired conclusions.

(c) 2003 Thomas G. Dietterich and Devika

Subramanian 10
(c) 2003 Thomas G. Dietterich and Devika
Subramanian 11
Rational agents do the best they can
given their resources

(c) 2003 Thomas G. Dietterich and Devika

Subramanian 12
 Rational Agents

very few resources lots of resources

no thought limited,
Careful, deliberate
approximate
“reflexes” reasoning
reasoning

 Adjust amount of reasoning according to

available resouces and importance of the
result
 This is one thing that makes AI hard
(c) 2003 Thomas G. Dietterich and Devika
Subramanian 13
Rational Agents

(c) 2003 Thomas G. Dietterich and Devika

Subramanian 14
(c) 2003 Thomas G. Dietterich and Devika
Subramanian 15
(c) 2003 Thomas G. Dietterich and Devika
Subramanian 16
2.3 The Nature of Environments
what does it mean to do the right thing?

(c) 2003 Thomas G. Dietterich and Devika

Subramanian 17
(c) 2003 Thomas G. Dietterich and Devika
Subramanian 18
(c) 2003 Thomas G. Dietterich and Devika
Subramanian 19
(c) 2003 Thomas G. Dietterich and Devika
Subramanian 20
Environ
ment Fully Observable vs. Partially
Observabl
Types Deterministic vs.
e
Stochastic
(vs.
Strat
Episodic vs. Sequential
egic)

Static vs.
Dynamic
(vs. Semi-Dynamic)
Discrete
vs.
Single-Agent Continuous

vs.
Known
Multi-Agent
27
 Fully Observable vs. Partia ly
o
Observable
Do the agent's sensors give it access to the complete state of the
environment?
o For any given world state, are the values
of all the variables known to the agent?

vs.

28
fully observable environment

(c) 2003 Thomas G. Dietterich and Devika

Subramanian 23
Deterministic vs. Stochastic (vs.
Strategic)

vs.

24
Deterministic vs. Stochastic (vs.
Strategic

(c) 2003 Thomas G. Dietterich and Devika

Subramanian 25
Episodic vs. Sequential

vs.

26
Pick and Place Robot

(c) 2003 Thomas G. Dietterich and Devika

Subramanian 27
(c) 2003 Thomas G. Dietterich and Devika
Subramanian 28
 Static vs. Dynamic (vs. Semi-
dynamic)
o Is the world changing while the agent is thinking?
o Semi-dynamic: the environment does not change
with the passage of time, but the agent's performance score
does.

vs.

29
 Discrete vs. Continuous
o Does the environment provide a fixed number of
distinct
percepts, actions, and environment states?
o Are the values of the state variables discrete or continuous?
o Time can also evolve in a discrete or continuous fashion.

vs.

30
Single–Agent vs. Multi–Agent

vs.

31
 Known vs. Unknown
o Are the rules of the environment (transition model and rewards
associated with states) known to the agent?
o Strictly speaking, not a property of the environment, but of the
agent’s state of knowledge.

vs.

32
Examples of the different
environments

33
 Example:Romania
- On vacation in Romania; currently in
Arad.
- Flight leaves tomorrow from Bucharest.

Initial state
oArad
Actions
oGo from one city to another
Transition Model
oIf you go from city A to
city B, you end up in city B
Goal State
oBucharest
Path Cost
oSum of edge costs (total distance traveled)
 Where are we now?

 SKICAT: a system for automatically classifying the

terabytes of data from space telescopes and
identifying interesting objects in the sky. 94%
classification accuracy, exceeds human abilities.
 Deep Blue: the first computer program to defeat
champion Garry Kasparov.
 Pegasus: a speech understanding program that is a
travel agent (1-877-LCS-TALK).
 Jupiter: a weather information system (1-888-573-
TALK)
 HipNav: a robot hip-replacement surgeon.

(c) 2003 Thomas G. Dietterich and Devika

Subramanian 35
 Areas of Study in AI
 Reasoning, optimization, resource allocation

planning, scheduling, real-time problem solving,
intelligent assistants, internet agents
 Natural Language Processing

information retrieval, summarization, understanding,
generation, translation
 Vision

image analysis, recognition, scene understanding
 Robotics

grasping/manipulation, locomotion, motion planning,
mapping

(c) 2003 Thomas G. Dietterich and Devika

Subramanian 36
 Where are we now?

 Navlab: a Ford escort that steered itself from

Washington DC to San Diego 98% of the way on its
own!
 google news: autonomous AI system that assembles
“live” newspaper
 DS1: a NASA spacecraft that did an autonomous flyby
an asteroid.
 Credit card fraud detection and loan approval
 Search engines: www.citeseer.com, automatic
classification and indexing of research papers.
 Proverb: solves NYT puzzles as well as the best
humans.
(c) 2003 Thomas G. Dietterich and Devika
Subramanian 37
 Surprises in AI research

 Tasks difficult for humans have turned out to

be “easy”
 Chess
 Checkers, Othello, Backgammon
 Logistics planning
 Airline scheduling
 Fraud detection
 Sorting mail
 Proving theorems
 Crossword puzzles

(c) 2003 Thomas G. Dietterich and Devika

Subramanian 38
 Surprises in AI research

 Tasks easy for humans have turned out to be

hard.
 Speech recognition
 Face recognition
 Composing music/art
 Autonomous navigation
 Motor activities (walking)
 Language understanding
 Common sense reasoning (example: how many
legs does a fish have?)
(c) 2003 Thomas G. Dietterich and Devika
Subramanian 39
 Artificial
Intelligence
Related
Disciplines

39
 Learning Agents?

"Of particular interest in AI are Learning agents, which are

capable of changing themselves given training examples or

through positive or negative feedback, such that the average

utility of their actions grows over time."

- Wolfgang Ertel, "Introduction to Artificial Intelligence," 2nd Edition (2017) 41

 Artificial Intelligence Vs.
Machine Learning Vs.
Deep Learning ..

Evolution of AI — Source: https:// 43

www.embedded-vision.com/
 Machine Learning Vs. Deep
Learning ..

https:// 44
www.upwork.com/hiring/for-clients/artificial-intelligence-and-natural-language-processing-in-big-data/
 Machine Learning?

G e n e r i cM a c h i n e Learni
ng Models 45
Machin
e
Learnin
g?
{ Artif i c i a l
I ntel l i gence }
Machine
Learning
Map

46
Machine Learning
Approaches & their
corresponding
Applications
47
 What about Data-Mining?
Machine learning and data mining often employ the same
methods and overlap significantly. They can be roughly
distinguished as follows:
oMachine learning focuses on prediction,
based on known
properties learned from the training data.
oData mining focuses on the discovery of (previously) unknown
properties in the data. This is the analysis step of Knowledge
Discovery in Databases.
Much of the confusion between these two research communities
comes from the basic assumptions they work with: in machine
learning, performance is usually evaluated with respect to the
ability to reproduce known knowledge, while in Knowledge
Discovery and Data Mining (KDD) the key task is the discovery of
previously unknown knowledge. 48
 Artificial Intelligence Vs. Data-
Science
DataScience-Some PossibleDefinitions:
Data Science is the science which uses computer science,
statistics and machine learning, visualization and human-
computer interactions to collect, clean, integrate, analyse,
visualize, interact with data to create data products.

Data science = statistics + data processing + machine learning +

scientific inquiry + visualization + business analytics + big data +
…

49
 WhyDataScience?
in 20th Century Innovations ..
Engineering and Computer Science played key
role:
oCars
oAirplanes
oPower grid
oTelevision
oAir conditioning and central heating
oNuclear power
oDigital computers
oThe internet

50
 WhyDataScience?
What is the difference? .. Data
oDoes fertilizer increase crop yields?

Answer: Collect and analyse agricultural experimental data.

oDoes Streptomycin cure Tuberculosis?

Answer: Collect and analyse randomized trials data.

oDoes smoking cause lung-‐cancer?

Answer: Collect and analyse observational studies data.

Deductive versus empirical ..

Solutions deduced mostly from theory versus solutions
deduced from mostly from data .. 51
 The Dawn of Big Data

To understand the
phenomenon that is big data,
it is often described using five
Vs: Volume, Velocity, Variety,
Veracity, and Value.

Recently, Visualization,
Virality, & Viscosity were
added (thus, Eight Vs) ..

Source: https:// 53
www.intechopen.com/books/artificial-intelligence-scope-and-limitations/prediction- of-cancer-
 The Dawn of Big Data
o Volume refers to the vast amounts of data generated every second.
o Velocity refers to the speed at which new data is generated and the speed
at which data moves around.
o Variety refers to the different types of data we can now use. In fact, 80%
of the world’s data is now unstructured, and therefore can’t easily be
put
into tables (think of photos, video sequences or social media updates).
o Veracity refers to the messiness or trustworthiness of the data. With
many forms of big data, quality and accuracy are less controllable.
o Value; It is all well and good having access to big data but unless we can
turn it into value it is useless.
54