Introduction to Artificial

Intelligence
 Goals of this
•
Course
This class is a broad introduction to
artificial
intelligence (AI)
o AI is a very broad field with many subareas
• We will cover many of the primary concepts/ideas
 Today’s Lecture
• What is intelligence? What is artificial intelligence?

• A very brief history of AI

o Modern successes: Stanley the driving robot

• An AI scorecard
o How much progress has been made in different aspects of AI

o An Activity: Game
 What is
Artificial
Intelligence?
Answer: The power of a machine to copy intelligent human behaviour.
Some Definitions
(I)
The exciting new effort to make
computers think … machines with
minds, in the full literal sense.
Haugeland, 1985
 Robots

Are they really intelligent?

A robot is only as smart as its initial program.

Answer: The power of a machine to copy and learn from intelligent human
behavior.
Some Definitions
(II)
Some Definitions
(III)
The study of how to make
computers do things at which,
at the moment, people are
better.

Rich & Knight, 1991

 Artificial Intelligence VS.
Robot
AI Robot

Programmed to think Programmed to do

Social Interaction Low level interaction

Learns Only as smart as

program
 Examples

1. CleverBot 2. Autonomous Cars

3. Drones 4. IBM Watson

Lets watch a video on AI

https://www.youtube.com/watch?v=ad79nYk2keg
 What is
• Intelligence?
Intelligence:
o “the capacity to learn and solve problems” (Websters dictionary)
o in particular,
• the ability to solve novel problems
• the ability to act rationally
• the ability to act like humans

• Artificial Intelligence
o build and understand intelligent entities or agents
o 2 main approaches: “engineering” versus “cognitive modeling”
 What is
Intelligence?
Artificial
(John McCarthy, Stanford University)
• 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.

• Yes, but what is intelligence?

Intelligence is the computational part of the ability to achieve goals in the world. Varying kinds and
degrees of intelligence occur in people, many animals and some machines.

• Isn't there a solid definition of intelligence that doesn't depend on relating it to human
intelligence?
Not yet. The problem is that we cannot yet characterize in general what kinds of computational
procedures we want to call intelligent. We understand some of the mechanisms of intelligence and not
others.
 What’s involved in
Intelligence?

• Ability to interact with the real world

o to perceive, understand, and act
o e.g., speech recognition and understanding and synthesis
o e.g., image understanding
o e.g., ability to take actions, have an effect

• Reasoning and Planning

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

• Learning and Adaptation

o we are continuously learning and adapting
o our internal models are always being “updated”
• e.g., a baby learning to categorize and recognize animals
History of AI
 The Branches of AI
Artificial intelligence

Symbolic Learning Machine Learning

Deep
Computer
Statistical Learning/
Robotics Vision/image
Learning Neural
processing Natur
Spee Network
Convo Recurr
ch al
lution ent
langu Com
Reco age
Neural
pute
Neural
gniti netwo Netwo
Proces r
on rk
Visio rk
sing
n
and
obje
ct
Reco
gniti
on

Watch video for reference: https://www.youtube.com/watch?v=2ePf9rue1Ao

3 Domains of AI
 Different Types of Artificial
Intelligence
1. Modeling exactly how humans actually
think

2. Modeling exactly how humans actually act

3. Modeling how ideal agents “should think”

4. Modeling how ideal agents “should act”

• Modern AI focuses on the last definition
o we will also focus on this “engineering” approach
o success is judged by how well the agent performs
 What’s involved in Intelligence?
(again)
• Perceiving, recognizing, understanding the real
world

• Reasoning and planning about the external

world

• Learning and adaptation

• So what general principles should we use to
achieve these goals?
 Acting humanly: Turing test

• Turing (1950) "Computing machinery and intelligence“

• "Can machines think?"

• "Can machines behave intelligently?“

• Operational test for intelligent behaviour: The

Imitation Game

• Suggests major components required for AI:

- knowledge representation
- reasoning,
- language/image understanding,
- learning

* Question: is it important that an intelligent system act like a human?

 The Origins of AI
• 1950 Alan Turing’s paper, Computing Machinery
and
Intelligence, described what is now called “The Turing Test”.
• Turin predicted that in about year "an average
interrogator will not
g have more than a s70 percent
fifty
making
chance of right after minutes of
the identification five
questioning"
.
• 1957 Newell and Simon predicted that "Within ten
years a computer will be the world's chess champion."
AI system

Experimenter

Control
ACTIVITY

GAME RULES
• The game of Rock, Paper, Scissors is very simple. Each
 ROCK PAPER SCISSORS player picks one of the three objects (usually by making
 the appropriate hand shape on a count of three!) and these
Rock, Paper & Scissors: A game based on Data for
rules are applied to see who has won that round
AI where the machine tries to predict
• :Paper wraps (beats) Rock
 the next move of the participant. It is a replica of
basic rock, paper and scissors game
• Scissors cut (beat) Paper
• Rock blunts (beats) Scissors
 where the machine tries to win ahead by learning
 The challenge of the game is to guess what your opponent
from the participant’s previous moves.
will choose and pick the appropriate object to beat them.
 http://www.cs.stir.ac.uk/~kms/schools/rp People find it quite hard to pick a sequence of perfectly
s/index.php random choices, so any pattern that a player develops
could be learned by the opponent and used to win the
game. That is what happens in this example. As you play,
the computer learns the pattern of objects that you are
most likely to pick.
 ACTIVITY 2

GAME To play
 Mystery Animal: A game based  Link for Game 2 (Mystery
on Natural Language Processing Animal):
where the participant has to https://experiments.withgoogle
guess the animal by asking .com/mystery-animal
maximum 20 questions to AI. The
animal randomly gets selected
for each game by AI and the
machine replies in either yes or
no.
 ACTIVITY 3- Emoji Scavenger
Hunt

GAME To play
 Locate the emoji the computer  Link for Game 3 (Emoji
show you in the real world with Scavenger hunt )
your phone’s camera. A neural https://emojiscavengerhunt.wit
network will try to guess what it’s hgoogle.com/
seeing.
Make sure your sound is on.
 Patient: You are like my father in some ways.
 Doctor: What resemblance do you see?
 Patient : You are not very aggressive.
 Doctor : What makes you think I am not very aggressive?
 Patient : You don’t argue with me.
 Doctor : Why do you think I don’t argue with you?
 Patient : You are afraid of me.
 Doctor : Does it please you to believe I am afraid of you?
 Patient : My father is afraid of everybody.
 Doctor : What else comes to mind when you think of your father?
 Patient : Bullies.

ELIZA was the very first chatbot as mentioned above. It was created
by Joseph Weizenbaum in 1966 and it uses pattern matching and
substitution methodology to simulate conversation. The program was
designed in a way that it mimics human conversation.
Thank
You