Chapter 11:

(1)

Chapter 11:

Artificial Intelligence

Computer Science: An Overview Eleventh Edition

by

J. Glenn Brookshear Dennis Brylow

(2)

Chapter 11: Artificial Intelligence

• 11.1 Intelligence and Machines

• 11.2 Perception

• 11.3 Reasoning

• 11.4 Additional Areas of Research

• 11.5 Artificial Neural Networks

• 11.6 Robotics

(3)

Intelligent Agents

• Agent: A “device” that responds to stimuli from its environment

– Sensors – Actuators

• Much of the research in artificial

intelligence can be viewed in the context of building agents that behave intelligently

(4)

Levels of Intelligent Behavior

• Reflex: actions are predetermined responses to the input data

• More intelligent behavior requires knowledge of the environment and involves such activities as:

– Goal seeking – Learning

(5)

Figure 11.1 The eight-puzzle in its

solved configuration

(6)

Figure 11.2 Our puzzle-solving

machine

(7)

Approaches to Research in Artificial Intelligence

• Engineering track

– Performance oriented

• Theoretical track

– Simulation oriented

(8)

Turing Test

• Test setup: Human interrogator

communicates with test subject by typewriter.

• Test: Can the human interrogator

distinguish whether the test subject is human or machine?

(9)

Techniques for Understanding Images

• Template matching

• Image processing

– edge enhancement – region finding

– smoothing

• Image analysis

(10)

Language Processing

• Syntactic Analysis

• Semantic Analysis

• Contextual Analysis

(11)

Figure 11.3 A semantic net

(12)

Components of a Production Systems

1. Collection of states

– Start (or initial) state – Goal state (or states)

2. Collection of productions: rules or moves

– Each production may have preconditions

3. Control system: decides which production to apply next

(13)

Reasoning by Searching

• State Graph: All states and productions

• Search Tree: A record of state transitions explored while searching for a goal state

– Breadth-first search – Depth-first search

(14)

Figure 11.4 A small portion of the

eight-puzzle’s state graph

(15)

Figure 11.5 Deductive reasoning in the context of a production system

(16)

Figure 11.6 An unsolved

eight-puzzle

(17)

Figure 11.7 A sample search tree

(18)

Figure 11.8 Productions stacked for

later execution

(19)

Heuristic Strategies

• Heuristic: A “rule of thumb” for making decisions

• Requirements for good heuristics

– Must be easier to compute than a complete solution

– Must provide a reasonable estimate of proximity to a goal

(20)

Figure 11.9 An unsolved

eight-puzzle

(21)

Figure 11.10 An algorithm for a control system using heuristics

Establish the start node of the state graph as the root of the search tree and record its heuristic value.

while (the goal node has not been reached):

Select the leftmost leaf node with the smallest heuristic value of all leaf nodes.

To this selected node attach as children those nodes that can be reached by a single production.

Record the heuristic of each of these new nodes next to the node in the search tree.

Traverse the search tree from the goal node up to the root, pushing the production associated with each arc traversed onto a stack.

Solve the original problem by executing the productions as they are popped off the stack.

(22)

Figure 11.11 The beginnings of our

heuristic search

(23)

Figure 11.12 The search tree after

two passes

(24)

Figure 11.13 The search tree after

three passes

(25)

Figure 11.14

The complete search tree

formed by our heuristic

system

(26)

Handling Real-World Knowledge

• Representation and storage

• Accessing relevant information

– Meta-Reasoning

– Closed-World Assumption

• Frame problem

(27)

Learning

• Imitation

• Supervised Training

– Training Set

• Reinforcement

(28)

Genetic Algorithms

• Begins by generating a random pool of trial solutions:

– Each solution is a chromosome

– Each component of a chromosome is a gene

• Repeatedly generate new pools

– Each new chromosome is an offspring of two parents from the previous pool

– Probabilistic preference used to select parents

(29)

Artificial Neural Networks

• Artificial Neuron

– Each input is multiplied by a weighting factor.

– Output is 1 if sum of weighted inputs exceeds the threshold value; 0 otherwise.

• Network is programmed by adjusting weights using feedback from examples.

(30)

Figure 11.15 A neuron in a living

biological system

(31)

Figure 11.16 The activities within a

processing unit

(32)

Figure 11.17 Representation of a

processing unit

(33)

Figure 11.18 A neural network with

two different programs

(34)

Figure 11.20 The structure of

ALVINN

(35)

Associative Memory

• Associative memory: The retrieval of information relevant to the information at hand

• One direction of research seeks to build

associative memory using neural networks that when given a partial pattern, transition themselves to a completed pattern.

(36)

Figure 11.21 An artificial neural

network implementing an associative

memory

(37)

Figure 11.22 The steps leading to a

stable configuration

(38)

Robotics

• Truly autonomous robots require progress in perception and reasoning.

• Major advances being made in mobility

• Plan development versus reactive responses

• Evolutionary robotics

(39)

Issues Raised by Artificial Intelligence

• When should a computer’s decision be trusted over a human’s?

• If a computer can do a job better than a human, when should a human do the job anyway?

• What would be the social impact if

computer “intelligence” surpasses that of many humans?