Transcript How can a computer be programmed to

Artificial Intelligence
Artificial Intelligence: Computations that make it possible for a
machine to perceive, reason, and act in a manner consistent with
human behavior.
The Turing Test
A human questioner inputs
questions and guesses which
respondent is human, based
on the answers given.
CS 111.01
Chapter 11 – Artificial Intelligence
Page 133
Image Analysis
Character Recognition: How can a computer be programmed to
distinguish between different letters of the alphabet?
A RBKHN
3D Perspective Recognition: How can a computer be programmed to
distinguish between separate 3D objects? To distinguish between
near and far objects? To determine which part of an object is
obscured by another object?
Trihedral Vertex Types
L-Vertex
Arrow Vertex
CS 111.01
Non-trihedral Figures
Fork Vertex
T-Vertex
Chapter 11 – Artificial Intelligence
Page 134
Natural Language Processing
Written Comprehension: How can a computer be programmed to
grasp the syntax and semantics of a natural language?
John saw the boy in the park with the telescope.
Question: Whose telescope is it?
Answer: John’s
John saw the boy in the park with the puppy.
Question: Whose puppy is it?
Answer: The boy’s
John saw the boy in the park with the statue.
Question: Whose statue is it?
CS 111.01
Answer: The park’s
Chapter 11 – Artificial Intelligence
Page 135
Speech Recognition and Generation
Speech Recognition: By segmenting
input sound patterns into individual
words, filtering out extraneous noise,
and following linguistic rules, a
computer can be made to recognize and
respond to verbal communication.
Speech Generation:
While prerecorded
speech may be used for
automated responses
(e.g., a “lights-on”
warning in a car),
synthesized speech is
being developed to
respond to more
random input.
CS 111.01
Chapter 11 – Artificial Intelligence
Page 136
Computer Reasoning
To simulate logical reasoning, heuristic functions are often used.
A heuristic is an artificial measure of how close the computer’s
current status is to its problem-solving goal.
F(config) =
(# of completable rows, columns, and
diagonals for X-player) – (# of completable
rows, columns, and diagonals for O-player)
if config is a non-winning
configuration

if config is an X-win
-
if config is an O-win
O O
X
X
1
-
X O O
O O
X
-
X
X O O
O X
X
2-1=1
X O O
X
X O
3-1=2
X O O
X
X
O
2-1=1
X O O
X O
X
3-1=2
O O O
X X
X
-
O O
X X
X
O O
X X
X O
3-2=1
2-2=0
O O
X X O
X
O O O
3-2=1
-
X
X X
O O
X
X
O O
O X
X X
2-2=0
X
O O
X X
O O
X X
X
O
X X
-
-
X
O O
X
X X O
2-2=0
O O
X O
X X
O O O
3-2=1
-
X
X
X
O O
O X
X
X
2-1=1
X
O O
X
X O X
3-1=2
O O O
O O
X X
O X X
X
2-1=1
X
-
O O
X X
X O
2-1=1
O O
X X
X
O
2-1=1
O O
X O
X
X
3-1=2
In the tic-tac-toe example above, when the computer is ready to make an X-move, it
uses the heuristic max{F(config), where config can be the result of any O-move}.
CS 111.01
Chapter 11 – Artificial Intelligence
Page 137
Neural Networks
To simulate learning, certain multiprocessor systems, called neural
networks, have been built to “learn” to recognize particular patterns
as correct or incorrect, based upon a trial-and-error process.
In the example below, a neural network is used to teach a
computerized system how to back a truck up to a loading dock.
The physical characteristics of the
truck are programmed, with the
relationship between the steering
wheel, the tires, the cab, and the
trailer formally calculated.
CS 111.01
Starting at some initial position, the
truck is backed up one meter at a time,
with programmed steering; the error in
the result is measured and factored into
the next attempt, until the error is zero.
Chapter 11 – Artificial Intelligence
Page 138
Expert Systems
By programming a computer with the assistance of experts in a
particular field, an expert system can be developed to perform very
specialized tasks.
CS 111.01
Chapter 11 – Artificial Intelligence
Page 139
Genetic Algorithms
When a problem has no definitive algorithmic solution, it’s possible
that a technique can be developed by which the solution can evolve.
This type of solution, known as a genetic algorithm, involves the
generation of numerous possible solutions, the best features of which
are “bred” together to mutate into an acceptable overall solution.
For example, in the example at left, the
problem of producing a flywheel
composed of a variety of ceramic,
polymer, and fiber materials is addressed.
The right balance of materials is desired
so the flywheel can spin faster (thus
producing greater kinetic energy), but not
so fast that the resulting shear forces will
rip the flywheel apart.
CS 111.01
Chapter 11 – Artificial Intelligence
Page 140
Robotics
Robots are programmable devices capable of
manipulating objects and performing tasks much like
humans are able to do.
CS 111.01
Chapter 11 – Artificial Intelligence
Page 141
Collision Avoidance, Detection, & Reaction
One of the more difficult problems when programming a robot is
determining when it is about to collide with something, when it has
collided with something, and what to do in response to a collision.
Collision Avoidance
Collision Detection
Use scanners to
Use sensors at
determine the robot’s strategically located
proximity to other
places on the robot
objects, redirecting the
to determine if a
robot when a collision
collision occurs.
is imminent.
CS 111.01
Chapter 11 – Artificial Intelligence
Collision Reaction
Go around?
Climb over?
Bounce back?
Run away?
Drop dead?
Page 142
Waiting On Robot’s Hand & Foot…
Other common human actions that are difficult to
program include propelled locomotion and manual
manipulation.
Walking Gait
How can a robot be
programmed to propel itself
forward on “legs” and still
maintain its balance?
CS 111.01
Grasping
How can a robot be
programmed to grasp part of a
stack of objects, without
toppling the rest of the stack?
Chapter 11 – Artificial Intelligence
Page 143
Entertainment Robotics
The toy-like appeal of robots has not been lost on the
entertainment industry.
Sony’s robotic dog can:
Lego’s robot building kits include:
• Respond to particular sounds
• Sensors that react to light, touch, heat
• Display moods based on attention/neglect
• Motors controlling wheels, pulleys, etc.
CS 111.01
Chapter 11 – Artificial Intelligence
Page 144