ARTIFICAL INTELLIGENCE FOR

ENGINEERING
(KMC-101/ 201)

UNIT: 1
An overview of AI

1
Evolution of AI to the
present

2
Intelligent Systems in Your Everyday Life
Social Networking
• Facebook

• When you upload photos to Facebook, the service automatically highlights

faces and suggests friends to tag.
• How can it instantly identify which of your friends is in the photo?

• Google uses AI to ensure that nearly all of the email landing in your inbox is
authentic. Their filters attempt to sort emails into the following categories
•Primary ,Social, Promotions, Updates, Forums, Spam

The program helps your emails get organized so you can find your way to important communications quicker.
3
 Chatbots

• Chatbots recognize words and phrases in order to (hopefully) deliver helpful content.

• Chatbots attempt to mimic natural language, simulating conversations as they help

with routine tasks such as booking appointments, taking orders etc.

• Sometimes, chatbots are so accurate that it seems as if you’re talking to a real person.

The chatbot conversation

in the image shows AI
being used

4
Intelligent Systems in Your Everyday Life

• Post Office
• automatic address recognition and sorting of mail

• Banks
• automatic check readers, signature verification systems
• automated loan application classification

• Telephone Companies
• automatic voice recognition for directory inquiries
• automatic fraud detection,
• classification of phone numbers into groups

• Credit Card Companies

• automated fraud detection, automated screening of applications

• Computer Companies
• automated diagnosis for help-desk applications
5
 Definitions-I

The exciting new effort to make computers think … machines with minds, in the full
literal sense. Haugeland, 1985
(exciting but not really useful)

Definitions-II

The study of mental faculties through the use of computational models.

Charniak and McDermott, 1985

A field of study that seeks to explain and emulate intelligent behavior in terms of
computational processes. Schalkoff, 1990

6
Definitions-III

The study of how to make computers do things at which, at the moment, people are
better.
Rich & Knight, 1991

7
What is Intelligence?

Intelligence:
• “the capacity to learn and solve problems”
(Websters dictionary)
• in particular,
• the ability to solve novel problems
• the ability to act rationally
• the ability to act like humans

8
What is artificial intelligence?
It is the science and engineering of making intelligent machines,
especially intelligent computer programs. 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.

(John McCarthy, Stanford

University)

9
What is (Artificial)Intelligence?
Intelligence can have many faces:
creativity, solving problems, pattern recognition, classification, learning, optimization,
surviving in an environment, language processing, planning, and knowledge.
⇒ formal definition incorporating every aspect of intelligence is difficult.

Fourpossibledefinitions ofAI

Systems that think like Systems that think rationally

humans

Systems that act like Systems that act rationally

humans 10
A Brief History of AI

• 1943: McCulloch and Pitts propose a model of artificial neurons

• 1956 Minsky and Edmonds build first neural network computer, the SNARC

The Dartmouth Conference (1956)

• John McCarthy organizes a two-month workshop for researchers interested in
neural networks and the study of intelligence
• Agreement to adopt a new name for this field of study: Artificial Intelligence

1952-1969 Enthusiasm:

• Arthur Samuel’s checkers player

• Shakey the robot
• Lots of work on neural networks 11
1966-1974 Reality:
• AI problems appear to be too big and complex
• Computers are very slow, very expensive, and have very little memory (compared to
today)

1969-1979 Knowledge-based systems:

• Birth of expert systems
• Idea is to give AI systems lots of information to start with

1980-1988 AI in industry:

• R1 becomes first successful commercial expert system

• Some interesting phone company systems for diagnosing failures of
telephone service
12
1990s to the present:
• Increases in computational power (computers are cheaper, faster, and have tons more
memory than they used to)
• An example of the coolness of speed: Computer Chess

13
What’s involved in Intelligence?
• Ability to interact with the real world
• to perceive, understand, and act
• e.g., speech recognition and image understanding
• e.g., ability to take actions
• Reasoning and Planning
• 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 14
 The Turing Test
• 1950 – Alan Turing devised a test for
intelligence called the Imitation
Game
• Ask questions of two entities, receive
answers from both
• If you can’t tell which of the entities is
human and which is a computer Questions
program, then you are fooled and we Answers Answers
should therefore consider the
computer to be intelligent

Which is the person?

Which is the computer? 15
Academic Disciplines important to AI
• Philosophy: Logic, methods of reasoning, mind as physical system, foundations of learning, language,
rationality.

• Mathematics: Formal representation and proof, algorithms, computation, (un)decidability, (in)tractability,

probability.

• Economics: utility, decision theory

• Neuroscience: neurons as information processing units.

• Psychology: how do people behave, perceive, process Cognitive Science information, represent
knowledge.
• Computer engineering: For building fast computers

• Linguistics: knowledge representation, grammar

16
Must an Intelligent System be Foolproof?

• A “foolproof” system is one that never makes an error:

• Types of possible computer errors
• hardware errors, e.g., memory errors
• software errors, e.g., coding bugs
• “human-like” errors
• Clearly, hardware and software errors are possible in practice
• An intelligent system can make errors and still be intelligent
• humans are not right all of the time
• we learn and adapt from making mistakes

• Conclusion:
• NO: intelligent systems will not (and need not) be foolproof

17
Can Computers play Humans at Chess?
• Chess Playing is a classic AI problem
• well-defined problem
• very complex: difficult for humans to play well

Garry Kasparov Deep Blue

Deep Thought
Points Ratings

Conclusion: YES: today’s computers can beat even the best human
18
Can Computers Recognize Speech?

• Speech Recognition:
• mapping sounds from a microphone into a list of words.
• Hard problem: noise, more than one person talking, speech
variability,..
• Even if we recognize each word, we may not understand its meaning
• Recognizing normal speech is much more difficult
• speech is continuous: where are the boundaries between words?
• large vocabularies
• can be many thousands of possible words
• background noise, other speakers, accents, colds, etc
• on normal speech, modern systems are only about 60% accurate

• Conclusion: NO, normal speech is too complex to accurately recognize,

• but YES for restricted problems
(e.g., recent software for PC use by IBM, Dragon systems, etc)
19
Can Computers Learn and Adapt ?
Machine learning allows computers to learn to do things without explicit
programming

• Conclusion: YES, computers can learn and adapt, when presented with
information in the appropriate way

Can Computers plan and make decisions?

• Real-world planning and decision-making is still beyond the

capabilities of modern computers
• exception: very well-defined, constrained problems: mission planning
for satellites.
20
Can Computers “see”?

• Why is visual recognition a hard problem?

• Conclusion: mostly NO: computers can only “see” certain types of objects under
limited circumstances: but YES for certain constrained problems (e.g., face
recognition)
21
Summary of AI Systems in Practice
• Speech synthesis, recognition and understanding
• very useful for limited vocabulary applications
• unconstrained speech understanding is still too hard
• Computer vision
• works for constrained problems (hand-written zip-codes)
• understanding real-world, natural scenes is still too hard
• Learning
• adaptive systems are used in many applications: have their limits
• Planning and Reasoning
• only works for constrained problems: e.g., chess
• real-world is too complex for general systems

• Overall:
• many components of intelligent systems are “possible”
• there are many interesting research problems remaining

22
AI Applications: Consumer Marketing
• Have you ever used any kind of credit/ATM/store card while shopping?
• if so, you have very likely been “input” to an AI algorithm
• All of this information is recorded digitally
• Companies like Nielsen gather this information weekly and search for patterns
How do they do this?
• Algorithms (“data mining”) search data for patterns
• based on mathematical theories of learning
• completely impractical to do manually

AI Applications: Identification Technologies

• ID cards
• e.g., ATM cards
• Biometric Identification
23
AI Applications: Predicting the Stock Market
Value of ?
the Stock

time in days
• The Prediction Problem
• given the past, predict the future
• very difficult problem!
• we can use learning algorithms to learn a predictive model from
historical data
• prob(increase at day t+1 | values at day t, t-1,t-2....,t-k)
• such models are routinely used by banks and financial traders to
manage portfolios worth millions of dollars
24
AI-Applications: Machine Translation

• Language problems in international business

• e.g., at a meeting of Japanese, Korean, Vietnamese and
Swedish investors, no common language
• solution; hire translators to translate
• would be much cheaper if a machine could do this!
• How hard is automated translation
• very difficult!
• e.g., English to Russian
• not only must the words be translated, but their meaning also!

25
26