Docsity
Docsity
Prepare for your exams
Prepare for your exams

Study with the several resources on Docsity

Earn points to download
Earn points to download

Earn points by helping other students or get them with a premium plan

Guidelines and tips
Guidelines and tips
Sell on Docsity
Sell on Docsity
Docsity AI
Docsity AI
Log inSign up

Prepare for your exams

Study with the several resources on Docsity

Find documents

Prepare for your exams with the study notes shared by other students like you on Docsity

Search for your university

Find the specific documents for your university's exams

Docsity AINEW

Summarize your documents, ask them questions, convert them into quizzes and concept maps

Explore questions

Clear up your doubts by reading the answers to questions asked by your fellow students

Earn points to download

Earn points by helping other students or get them with a premium plan

Share documents
download point icon20 Points

For each uploaded document

Answer questions
download point icon5 Points

For each given answer (max 1 per day)

All the ways to get free points
Get points immediately

Choose a premium plan with all the points you need

Study Opportunities

Choose your next study program

Get in touch with the best universities in the world. Search through thousands of universities and official partners

Community

Ask the community

Ask the community for help and clear up your study doubts

Free resources

Our save-the-student-ebooks!

Download our free guides on studying techniques, anxiety management strategies, and thesis advice from Docsity tutors

Artificial Intelligence: An Introduction to Concepts and Applications - Prof. Lonnie E. Ch, Study notes of Computer Science

Christopher Newport University (CNU)Computer Science
Prof. Lonnie E. Cheney

An introduction to artificial intelligence, covering topics such as intelligence and machines, understanding images, reasoning, artificial neural networks, and other areas of research. It also discusses the psychology behind ai, the problem of intelligence, perception, production systems, control systems, neural networks, and applications of ai. Examples and case studies are used to illustrate these concepts.

Typology: Study notes

Pre 2010

Uploaded on 08/19/2009

koofers-user-tgo
koofers-user-tgo 🇺🇸

9 documents

1 / 12

Toggle sidebar

This page cannot be seen from the preview

Don't miss anything!

bg1
1
Introduction to Computer Science
Artificial Intelligence
Dr. Lonnie Cheney
Slide 2
Outline
Intelligence and Machines
Understanding Images
Reasoning
Artificial Neural Networks
Other Areas of Research
Slide 3
Outline
Intelligence and Machines
Understanding Images
Reasoning
Artificial Neural Networks
Other Areas of Research
Slide 4
What is AI?
• what is intelligence?
• perception+reasoning in unexpected situations?
• natural language understanding?
• problem solving? knowledge?
• computers
• execute algorithms with speed and accuracy
• predefined tasks ONLY
• humans
• reason about unexpected events
• understand, interpret, and comprehend results
pf3
pf4
pf5
pf8
pf9
pfa

Partial preview of the text

Download Artificial Intelligence: An Introduction to Concepts and Applications - Prof. Lonnie E. Ch and more Study notes Computer Science in PDF only on Docsity!

Introduction to Computer Science

Artificial Intelligence

Dr. Lonnie Cheney

Slide 2

Outline

 Intelligence and Machines

 Understanding Images

 Reasoning

 Artificial Neural Networks

 Other Areas of Research

Slide 3

Outline

 Intelligence and Machines

 Understanding Images

 Reasoning

 Artificial Neural Networks

 Other Areas of Research

Slide 4

What is AI?

  • what is intelligence?
    • perception+reasoning in unexpected situations?
    • • natural language understanding?problem solving? knowledge?
  • computers
    • • execute algorithms with speed and accuracypredefined tasks ONLY
  • humans
    • • reason about unexpected eventsunderstand, interpret, and comprehend results

Slide 5

Psychology

  • in order to design machines with AI, we need to understand more how human mind works
  • CS goal is a better machine, PSYC goal is better understanding of human mind
  • intelligence as “performance”
  • intelligence as “human-like”
  • example: tic tac toe, poker

Slide 6

Problem of Intelligence

  • no clean definition; not a matter of “yes/no”
  • operational definition: Turing test
  • if a human when conversing with another entity can’t tell if the other entity is machine or human, the entity is said to be intelligent
  • ELIZA, DOCTOR, PARRY, A.L.I.C.E.

Slide 7

The Eight-Puzzle

Slide 8

A Model “AI” Machine

  • camera: used for image processing
  • gripper and tool used for manipulation
  • problem domain: 8-puzzle solving

Slide 13

Feature Extraction

C: two horizontal bars, one verticalvertical joins horizontal at left edges of horizontals

Slide 14

Outline

 Intelligence and Machines

 Understanding Images

 Reasoning

 Artificial Neural Networks

 Other Areas of Research

Slide 15

Reasoning

  • give machine a goal and a start position, let it figure out how to get there
  • production system:
    • states: set of all values in the system at a certain point
      • start state: state system is initially in– goal state: state when problem is solved
    • • productionscontrol system: rules for how to change states: mechanism for choosing which production to apply

Slide 16

State Graph

Slide 17

Control Systems

  • finding the right path = picking the right productions
  • general methods for finding paths in a graph
  • will work on ANY problem expressible as a graph
  • brute-force method (try everything)
  • heuristics (use rule of thumb)

Slide 18

Brute-force: Search Trees

  • in the state graph, start at start state, and list all states reachable using only one production
  • repeat above for each new state reached until the goal state is found
  • problem of combinatorial explosion
  • eliminate redundant states

Slide 19

Sample Search Tree

Slide 20

Sample Search Tree

Slide 25

Applying Heuristics

  • from the start state, list all reachable states
  • for each reachable state, calculate the cost function
  • select the state with lowest cost and list all states reachable from it
  • repeat the cost calculations and selections until the goal state is reached
  • see textbook pp. 418

Slide 26

Example for 8-Puzzle

Slide 27

Outline

 Intelligence and Machines

 Understanding Images

 Reasoning

 Artificial Neural Networks

 Other Areas of Research

Slide 28

Neural Networks

The real thing: a neuron in a living biological system

Human brain:~ 10 (^11) neurons with about 10 (^4) synapses per neuron

Slide 29

Neural Networks

  • set of simple processing elements connected in layers• each unit maps a set of inputs to one output, based on
  • multiply each input by its weight. if the sum of these productsinput weights and a threshold exceeds the threshold, output a 1, else 0

Slide 30

Example Neural Net

Slide 31

OCR and Neural Nets

  • problem is to detect “C” or “T”
  • net has two levels: lower level has 9 inputs per unit while upper level has 1 input for each lower level
  • each lower level unit scans a 3x3 area of the field of view (hence the 9 inputs)
  • an active pixel in the field of view produces an input of 1

Slide 32

Problem: Recognize …

Slide 37

Outline

 Intelligence and Machines

 Understanding Images

 Reasoning

 Artificial Neural Networks

 Other Areas of Research

Slide 38

Applications of AI

  • natural language understanding
  • robotics
  • database systems
  • expert systems

Slide 39

Natural Language

  • requires understanding the meaning of the sentence (compilers work with well-defined semantics)
  • humans frequently don’t say literally what they mean (do you know what time it is?)
  • humans don’t strictly obey correct syntax
  • human language changes over time!
  • requires general knowledge (of the world)

Slide 40

Stages

  • syntactic analysis/parsing:
    • John gave Jim a pencil
    • Jim received a pencil from John
  • semantic analysis
    • meaning: the pencil that was with John is now with Jim.Both statements are equivalent.
  • contextual analysis
    • “The bat flew from his hand.”
    • meaning depends on context

Slide 41

Robotics

  • mechanical operations in a controlled environment
  • example: packing operations
  • not really intelligent, but precise timing and movement

Slide 42

Robotics and AI

  • in uncontrolled environment timing doesn’t work
  • example: sorting operations
  • items arrive all jumbled up in a box
  • robot must pick out items from the box and place them into different bins
  • must plan moves, perceive/recognize shapes of items

Slide 43

Database Systems

  • DBMS query languages are not natural
  • end users should not have to know a complicated query language (frequently they have no time to learn that language)
  • use AI to produce a natural language query system for such end users
  • be able to retrieve or INFER information

Slide 44

DB and AI

query language: select all records where lname = “smith” and fname = “john” or fname = “jim” and yearsEmploy > 9

natural language: do we have any senior executives by the name of J. Smith?