Artificial Intelligent Systems

Subject description

· Introduction to artificial intelligent systems: artificial perception, artificial intelligence, soft computing, machine learning, autonomous agents, and ambient intelligence, smart surveillance systems.

· Intelligent problem solving: problem decomposition and reduction, graph representation of problems, and graph search – exhaustive and heuristic search algorithms.

· Case study: assembly automation.

· Expert systems: expert-system components and human interfaces, procedural and declarative knowledge, and reasoning process.

· Knowledge representation: production rules, fuzzy production rules, and representation based on the Petri nets.

· Inference: forward and backward chaining, propositional calculus, predicate calculus, fuzzy inference, and probabilistic inference.

· Case study: knowledge-based computer-vision systems.

· Knowledge from experimental data: multivariate regression with artificial neural networks.

· Multi-agent systems: intelligent agent, multi-agent platforms, agent communication language.

Case study: FIPA-compliant multi-agent platform.

The subject is taught in programs

Objectives and competences

The objective of the course is to provide the student with the knowledge of basic mathematical and computational approaches in the development of artificial intelligence. The student is acquainted with the basic concepts of artificial intelligent systems and with the examples of the implementations of such systems. The acquired knowledge of soft computing, machine learning, and knowledge-representation forms enables the basic design and development of expert systems, autonomous intelligent agents, as well as multi-agent applications.

Teaching and learning methods

The lectures provide a theoretical background of all the considered models and methods together with simple computational examples that illustrate the key characteristics of all the presented methods. Lectures notes with the slides from the lectures are available to the students as the basic study material. As part of the lectures, the students receive optional homework assignments including theoretical questions as well as computational exercises that enable the students to promptly verify the acquired knowledge. Practical work is carried out as part of the laboratory exercises, where the students solve the given programming tasks. As part of the laboratory exercises, students also carry out additional elective projects within which they implement selected artificial intelligent systems or one of their key components for the selected fields of application, or alternatively, they carry out in-depth studies of existing artificial intelligent systems. The results of the elective projects are reported in written reports.

Expected study results

After successful completion of the course, students should be able to:

present the basic idea and sub-areas of artificial intelligence according to the content, research and application area,
describe the basic concepts and components of autonomous agents and other artificial intelligent systems that are supported by the problem-oriented knowledge bases and reasoning mechanisms, and having the ability to perceive environment, communicate with speech, self-learn and adapt to new circumstances,
explain the basic methods of soft computing and various knowledge-representation forms in intelligent systems,
model certain mental functions of human, such as learning and solving problems,
use the methods for searching for optimal solutions considering input data and knowledge base that is based on the use of one of the knowledge-representation forms,
search for regularities in data using the methods of automatic pattern recognition and data mining, and
to evaluate the accuracy and reliability of artificial intelligent systems.

Basic sources and literature

S. J. Russell, P. Norvig: Artificial Intelligence: A Modern Approach, Prentice Hall, 2010.
Mohri M., Rostamizadeh A., Talwalkar, A. : Foundations of Machine Learning, The MIT Press, 2012.
N. Pavešić, Razpoznavanje vzorcev: uvod v analizo in razumevanje vidnih in slušnih signalov, (3. popravljena in dopolnjena izd., 2 zv.), Založba FE in FRI, 2012