web analytics
+234 809 053 5932

OAU CPE 316 – Introduction To Artificial Intelligence PDF

OAU CPE 316 – Introduction To Artificial Intelligence PDF


CPE 316: Introduction to Artificial Intelligence
Rain Semester, 2014-2015 Session
Course Outline & Schedule
1 Introduction 2
1.1 Aim . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 2
1.2 Learning outcomes . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 2
1.3 Instruction principle . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 3
2 Course contents 3
2.1 Basic concepts . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 3
2.2 Knowledge representation in AI . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 4
2.3 Knowledge processing in AI . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 4
2.4 AI Systems development . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 5
3 Practical 6
4 Assessment 7
5 Lecture Timetable and Schedules 7
6 Textbooks 8
7 Course Webpage 8
8 Students with special needs 8
1. Mrs. T. O. OYEG OK ´ E
2. Dr. (Mrs.) D. O. NINAN
3. ’Tunj ´ ´ ı O . DE ´ . JO . B´ I (Coordinator); Room MB109, Computer Buildings.
1 Introduction
In this course, we will be inviting you to a discourse on the subject of Artificial Intelligence (AI) which is perhaps, the most controversial, and at the same time most interesting,
area in computer science and engineering. For a start, the terms that constitutes the title,
that is Artificial and Intelligence, are inherently ambiguous. For instance, the definition
of intelligence, and the basic concepts surrounding it, provokes vigorous debates among
experts in diverse fields of human endeavours. Central to these controversies is the interdisciplinary character of the discipline of AI as its subjects cut across several disciplines
including: computing, cognitive science, philosophy, physiology, sociology, biology, and
so on.
At a personal level, we all seem to recognise intelligent behaviour when we experience it, but we are unable to agree on a description of our experiences. For example,
we know that intelligence involves the ability to idealise, conceptualise, abstract and relate with our environment through our senses and our capability to use these in thinking,
reasoning, reflecting and projecting. The quality of the creativity exhibited by these capabilities is constrained by our world-view, awareness, consciousness, experience, skill,
emotion and intuition. The faculty of language is central to all these human endeavour.
At the moment, experts are yet to agree on a set of variables and/or parameters that will
allow us to articulate a definitive description of each of these concepts and the process
through which their interactions culminate in accounting for human intelligence.
Despite these, however, a number of systems that exhibits some semblance of complex problems solving capability, that has been construed as intelligence, have being developed. We will discuss how this has been achieved and issues relating to the criteria for
measuring and categorising them into class of intelligent systems.
1.1 Aim
The subject of focus in this course is the basic concepts and principles of the science
and engineering of “intelligent” systems. We will also discuss their possible applications.
Issues relating to the implications and ethics of their applications in human society will
also be highlighted as necessary.
1.2 Learning outcomes
By the end of this course, students would have been exposed to a sequence of instructions
and practises that are expected to facilitate an appreciation of the field of AI as it relates
to computing. The specific focus of discourse will include the following:
1. Putative definitions of basic concepts of intelligence; its philosophy, science and
2. Theories and criteria for intelligence;
3. Brief history of AI;
4. Current limitations and controversies surrounding IA;
5. AI systems development and deployment;
6. Selected Sub-fields of AI; Established AI products as well as the tools, methods and
techniques currently being used in Intelligent Systems (IS) science and engineering;
7. Social issues in IS application.

1.3 Instruction principle
Efforts will be made to teach and educate students on the general theories and principles
of Intelligent Systems. However, students are advised that although a number of achievements have been recorded in recent times, there is still a lot to be known definitively and
many more to be understood in the field of AI. This is partly due to: (i) misconceptions
and controversies surrounding the nature of intelligence and; (ii) the idea that intelligence
can, in principle, be mechanise despite (i).
2 Course contents
By the end of this course, we hope to discuss the following topics at a level of detail
appropriate for undergraduate studies.
2.1 Basic concepts
1. Definition and concepts of: Artificial, Intelligence, Artificial Intelligence (AI), Intelligent Systems; Fundamental items in AI perception: {Nature, Person(Self/Otherselfs),
Reality}, Knowledge, Thinking, Reasoning, Heuristics, Language, conventional computing and AI;
2. History of AI
3. Features of modern IS, test for intelligence (Alan Turing Test of intelligence and
John Searle’s “Chinese room” thought-experiment). Dilemma of AI: The signifiersignified dilemma, The whole-part dilemma.
4. Sub-fields and successful applications of AI: Robotics, Machine vision, Speech synthesis, speech/speaker recognition, Intelligent Process Control, Games, Decision
support systems, Story Generation Systems, Machine Translation Systems, Recommender systems, Text summarisers system, etc.
5. Introduction of course case studies:
O </i>
<i>ta </i>the <i>Ayo
game agent.
Kok or o </i>the ant.
• <i>Apalar ´ a ´ </i>the robot arm.
• <i>E</i>
<i>ni anun
2.2 Knowledge representation in AI
1. The concepts, theories and types of knowledge.
2. Knowledge representation techniques.
• Semantic networks
• Frames
• Formal methods
• Scripts
• Rules
• Trees and graphs
3. Selecting knowledge representation formalism for an application.
4. Introduction to ontologies.
2.3 Knowledge processing in AI
1. Issues in knowledge processing.
2. Knowledge processing paradigm (breadth first/depth first; forward/backward chaining).
3. Models of reasoning
• Monotonic reasoning
• Non-monotonic reasoning: with and without consistent proposition.
4. Planning.
5. Constraint satisfaction in modelling and planning.
6. Processing logic.
• Binary logic: proposition and predicate calculi.
• Multi-value logic.
• Hard and Soft logic
• Fuzzy-logic.
7. Genetic algorithms
8. Artificial Neural Networks
9. Fractals
10. Support vector matrix (SVM)
2.4 AI Systems development
Specifically the following stages in intelligent systems engineering will be demonstrated
using case problems and examples:
1. Understand the problem: Get a clear understanding of the problem in terms of the
behaviour of the intelligent system you which to mimic. Case examples of the possible input/output characteristics of the system can be very helpful in this task. Note
that, unlike conventional computational systems, some characteristics of intelligent
systems are implicit and, therefore, not directly observable or described definitively.
2. State assumptions: State all assumptions you are making regarding your proposed
model of intelligence. The assumption must, first of all, take cognisance of the nature
and capability of the system under study. Make sure that you are able to justify your
assumptions using reasonable arguments. Assumptions justified using arguments
relating to the environment in which the system will work, the resource available for
solving the problem, the target users of the problem, etc. will be appropriate.
3. Behaviour analysis: This comprise: (i) Stimuli/Response Identification. Identify each
and every relevant stimuli(input) to the intelligent system and the corresponding response(output) of the system. Label them using an appropriate variable. Note that
some intelligent systems do not have explicit stimuli, while some stimuli may not
generate explicitly or directly observable response. This will result in the statement
of functional and non-functional attributes that will be implemented. (ii) Solution
identification: A careful study of the alternative solution approach and selection of
the most appropriate one.
4 Design : Analyse and represent the behaviour of the intelligent systems using appropriate tools such as semantic network, heuristics, language model, state transition
information, plan, etc. These tools are very useful in representing and exploring the
behaviour of an intelligent system. A lot of information about the intelligence of a
system can be obtained from its language.
5. Implementation: Reduce the behaviour analysed into a mechanical process through
software or programming language codes and test the system with example problems. Note the implementation of intelligent systems, such as Robot, require collaboration with people in other discipline. The implementation of a robot hardware
components, for example, will usually required collaboration with professional such
as mechanical and electronics engineers.
6. Evaluation: The functionality and process of the system will be tested and the results
of the test documented.
3 Practical
We hope to have a number of laboratory classes in this course. Details shall be provided
during lectures. We expect to carry out the laboratory using the following case problems:
1. O </i></b>
<b><i>ta </i></b><b>the gamer</b>: This exercise involves the design and implementation of the thinking
employed by an agent playing <b><i>Ayo
, a two-person, complete information zero-sum
2. Kok or o ` the ant: This exercise involves the design and implementation of the locomotion of a simple six-legged ant and the co-ordinations of the movements of a
number of such ants in a colony.
3. Apalar ´ a ´ the robot arm: In this case example we shall discuss the design and simulation of a robot arm system as well as its control plan.
4. E
ni Anun ´ puzzle: In this exercise we shall discuss the analysis, design and implementation of a solution to the E
ni Anun ´ puzzle. This puzzle involves the determination of the most efficient means of searching for a missing person, using a party of
three other persons that sets out from a location with many plausible paths.
4 Assessment
Tentatively, credits will be awarded as shown in Table 1. You are however reminded that
the motto of this University is “For Learning and Culture”. We therefore expect and
encourage your responsible behaviour during and after this course. The co-ordinator will
be happy to receive your feedback in the form of comments, complaints and suggestions
that can improve your learning experiences in this course. You can reach him in Room
MB109, Computer Buildings Complex. You can also drop a note in his Pigeon hole in
Room MB208. At some point during, or about the end, of the course, you will be required to return a questionnaires that elicits your overall assessment of the course. Please
download the Course Assessment Form (CAF) from the course website.
Table 1: Award of credits
Components Percentage of total mark (%)
Laboratory and assignments 20
Continuous Assessment 20
Final Examination 60
Total 100
5 Lecture Timetable and Schedules
The tentative timetable for the course is:
Day : Wednesday
Time : 8:00 to 10:00 am (Morning)
Venue: BOOB
This will be discussed further during the first lecture.
NOTE: The Mid-Semester test is tentatively scheduled for the second (2nd) Saturday in January (January 9, 2016).



There are no reviews yet.

Be the first to review “OAU CPE 316 – Introduction To Artificial Intelligence PDF”

Your email address will not be published. Required fields are marked *