AI programming. State space representation and search. Heuristics. Planning. Game playing. Knowledge representation. Knowledge-based systems. Natural language processing. Machine learning. Reasoning under uncertainty. Philosophical issues.

cobblerbeggarAI and Robotics

Oct 15, 2013 (4 years and 26 days ago)

93 views



MA S S E Y U N I V E R S I T Y

COLLEGE OF SCIENCES

Important Information about the paper



Paper Number and Title:
159302

Artificial Intelligence


Credits value:


15

Semester:

1
2
01


Campus:

Albany

Mode:

Internal


Calendar Prescription
:


AI programming. State
space representation and search. Heuristics. Planning. Game
playing. Knowledge representation. Knowledge
-
based systems. Natural language
processing. Machine learning. Reasoning under uncertainty. Philosophical issues.


Pre
-
requisites:

159.201 or 159.202 or

159.211

Co
-
requisites:



Restrictions:

159.318


E
-
Learning Category:


N/A


Paper Coordinator:

Dr
.

Napoleon

H.

Reyes


Office:

QA 2.56




Email:

N.H.Reyes@massey.ac.nz

Phone:

9512


Secondary Contact: N/A


Learning Outcomes:

On successful co
mpletion a student should be able to:

1.

Describe the main Artificial Intelligence techniques used in computing.

2.

Design and program computers to store and manipulate knowledge.

3.

Describe, and in some cases program, the special techniques that can be used
to pe
rform intelligent tasks such as searching, game playing, natural
language processing and machine learning by computers.

4.

Understand and use logic for inference and fuzzy logic and some of its
applications

5.

Identify the advantages and disadvantages of applyi
ng various AI techniques
in solving real world problems through exploring the various applications of
AI.


Additional Requirements for Paper Completion

To pass, students have to obtain a cumulative assessment score greater than or equal to 50%.


Final exam
ination dates:
http://www.massey.ac.nz/massey/study/exam/timetables/timetables_home.cfm


Timetable:

http://www.massey.ac.nz/massey/study/class
-
timetable/class
-
t
imetable_home.cfm

Monday 12:00
-

13:00 AT8

Thursday 12:00
-

13:00 AT8

Friday 12:00
-

13:00 AT5



Textbook and Other Recommended Reading, Online Resources:



Russell, S. and Norvig, P., Artificial Intelligence A Modern Approach, Third Edi
tion,

(Prentice Hall 2010), ISBN
-
13: 978
-
0
-
13
-
604259
-
4



Notes, assignment proposals, assignment submission, code examples at:
www.massey.ac.nz/~nhreyes




Percentage

Deadline of submission

Assignment 1

20%
of the available marks

April 5

Assignment 2

20% of the available marks

June
1

Final Exam

60% of the available marks




Lecture Outline and Teaching Schedule


Week 1. Introduction, Problem Solving Paradigm



Film viewing



Demonstration of AI applications



Tutorial: Simulation Essentials for the assignments



Introduction to Search



Background and Motivation



Examples of Graphs



Problem Solving Paradigm



Graph Search as Tree Search



Terminologies



Classes of Search



Week 2. Any
-
Path Search Examples



Depth
-
First Al
gorithm



Breadth
-
First Algorithm



Best
-
First Search Algorithm



Search Strategies



Issues of Implementing the Search Strategies



Analyses of Worst Case Scenarios

o

Cost and Performance

o

Any
-
Path Search (Uninformed and Informed, Using the Visited List)

o

Depth
-
First A
lgorithm

o

Breadth
-
First Algorithm

o

Best
-
First Search Algorithm



Tutorial: Problem Solving: Any
-
Path Search Algorithms


Week 3. Optimal Search: Part 1



Optimal Uninformed Search



Uniform Cost Search



Why not a Visited List?



Implementing Optimal Search Strategi
es



Optimal Informed Search



The A* Algorithm, Heuristics, Using the Strict Expanded List)



Tutorial: Problem Solving: Optimal Search Algorithms


Week 4. Optimal Search: Part 2



The A* and Expanded List



Uniform Cost and Strict Expanded List





Consistency



Optim
ality and Worst Case Complexity



Tutorial: Problem Solving: Optimal Search Algorithms


Week 5 & 6. Fuzzy Logic



Fuzzification & Defuzzification



Fuzzy logic operators



Fuzzy Inference Systems



Fuzzy Control Systems



Case Studies: Inverted Pendulum Problem, Ro
bot Navigation (Obstacle Avoidance
and Target Pursuit, Fuzzy Colour Processing



Tutorial: Problem Solving: Hand
-
simulation of the Complete Fuzzy Inference
System


Week 7 & 8. Machine Learning



Introduction to Neural Networks



Neural Network Architectures



B
ackpropagation Learning Algorithm



Case Study: Application to Pattern Recognition



Tutorial: Problem Solving: Backpropagation Learning Simulation by hand


Week 9. Constraint Satisfaction Problems and Games: Part 1



Binary CSP



Constraints



Constraint Propag
ation (Arc Consistency)



Constraint Propagation Example



Backtracking and Constraint Propagation



Backtracking with Forward Checking (BT
-
FC)



Tutorial: Problem Solving: Graph Colouring Problem


Week 10. Constraint Satisfaction Problems and Games: Part 2



BT
-
F
C with Dynamic Ordering



Incremental Repair



Introduction to Games



Board Games and Search



Alpha
-
Beta Pruning



Practical Matters



Tutorial: Problem Solving: Minimax, Alpha Beta Pruning.


Week 11. Thinking Logically



Syntax, Semantics, Proof System, Sentence
s



Logical Operators, Operator Truth Table



Inference Rules



Proofs


Week 12. Review for Finals