ARTIFICIAL INTELLIGENCE

Type of course:	Compulsory
Language of instruction:	English
Erasmus Language of instruction:	English
Name of lecturer:	Maria Viorela Muntean
Seminar tutor:	Maria Viorela Muntean
Form of education	Full-time

Form of instruction:	Class
Number of teaching hours per semester:	56
Number of teaching hours per week:	4
Semester:	Autumn
Form of receiving a credit for a course:	Grade
Number of ECTS credits allocated	6

Course aims:

The course is a coherent introduction in Artificial Intelligence area, including theoretical and practical approaches.
The identification of appropriate models and methods for solving real-life problems.
The use of methodologies, specification mechanisms and development environments for the development of computer applications.
The use of computer and mathematical models and tools to solve specific problems in the application field.
Students will deal with the two AI approaches: symbolic and conexionist and they will use AI applications and languages.

Course Entry Requirements:

Fundamental Algorithms

Course contents:

1. INTRODUCTION 1.1. AI definitions 1.2. Short hystory of AI 1.3. AI components 1.4. AI applications 1.5. Knowledge based information systems. 2. PROBLEM SOLVING 2.1. Solving Problems by Searching 2.2. Uninformed Search Strategies 2.3. Informed (Heuristic) Search Strategies 3. OTHER PROBLEM SOLVING STRATEGIES 3.1. Constraint Satisfaction Problems 3.2. Adversarial Search (games) 4. KNOWLEDGE REPRESENTATION 4.1. Knowledge definitions and classification 4.2. Propositional Logic 4.3. First-Order Logic 5. KNOWLEDGE REPRESENTATION BY RULES 5.1. Types of rules 5.2. Rule based system's structure 5.3. Inference cycle 5.4. Reasoning. Forward chaining. Backward chaining. 6. STRUCTURED KNOWLEDGE 6.1. Semantic networks 6.2. Frames 7. UNCERTAIN KNOWLEDGE AND REASONING (FUZZY) 7.1. Introduction in fuzzy logic and reasoning 7.2. Examples of using fuzzy logic 8. PLANNING AND LEARNING IN AI SYSTEMS 8.1. Planning Approaches 8.2. Learning. Types of learning 9. ARTIFICIAL NEURAL NETWORKS FOUNDATIONS 9.1. Models of neurons an networks 9.2. An ANNs classification 9.3. Feed forward networks. Back propagation method 10. RECCURENT AND SELF ORGANIZING ANNs 10.1. Auto associative memories 10.2. Kohonen self organizing networks 11. MODERN ANNs ARCHITECTURES 12.1. ART network 12.2. Fuzzy ANNs 12.3. Radial basis functions networks 12. ANNs APPLICATIONS 13.1. Applications in images processing and recognition 13.2. Handwritten text recognition 13 EXPERT SYSTEMS FOUNDATIONS 14.1. Expert systems definitions 14.2. Expert systems architecture 14.3. Expert systems applications

Teaching methods:

Lecture, conversation, exemplification

Learning outcomes:

Minimum performance standard: minimum 5 at each evaluation criteria

Learning outcomes verification and assessment criteria:

Course Final evaluation Written paper 40%Theory assignment (test, last course) Written 20%Seminar/laboratory Continuous assessment Laboratory activities portfolio 40%