Učni načrt predmeta

Predmet:
Omrežni inteligentni sistemi in agenti
Course:
Network Intelligent Systems and Agents
Študijski program in stopnja /
Study programme and level		 Študijska smer /
Study field		 Letnik /
Academic year		 Semester /
Semester
Informacijske in komunikacijske tehnologije, 2. stopnja Inteligentni sistemi in robotika 1 1
Information and Communication Technologies, 2nd cycle Intelligent Sytems and Robotics 1 1
Vrsta predmeta / Course type
Izbirni / Elective
Univerzitetna koda predmeta / University course code:
IKT2-882
Predavanja
Lectures		 Seminar
Seminar		 Vaje
Tutorial		 Klinične vaje
work		 Druge oblike
študija		 Samost. delo
Individ. work		 ECTS
60 30 60 450 20

*Navedena porazdelitev ur velja, če je vpisanih vsaj 15 študentov. Drugače se obseg izvedbe kontaktnih ur sorazmerno zmanjša in prenese v samostojno delo. / This distribution of hours is valid if at least 15 students are enrolled. Otherwise the contact hours are linearly reduced and transfered to individual work.

Nosilec predmeta / Course leader:
prof. dr. Matjaž Gams
Sodelavci / Lecturers:
Jeziki / Languages:
Predavanja / Lectures:
slovenščina, angleščina / Slovenian, English
Vaje / Tutorial:
Pogoji za vključitev v delo oz. za opravljanje študijskih obveznosti:
Prerequisites:

Zaključen študijski program prve stopnje s področja naravoslovja, tehnike ali računalništva.

Student must complete first-cycle study programmes in natural sciences, technical disciplines or computer science.

Vsebina:
Content (Syllabus outline):

Znanstvena metoda: strukture znanstvenega védenja, znanstvene aktivnosti in procesi.

Uvod: definicije inteligentnih sistemov, umetne inteligence, agentov.

Informacijska družba: kratek pregled razvoja informacijske družbe, osnovnih zakonov informacijske družbe, značilnosti, trendi, umetna inteligenca, inteligentne storitve, novo poslovanje.

Inteligentni sistemi: lastnosti, področja, trendi, prednosti in slabosti, primeri; samostojni sistemi: ekspertni sistemi, nevronske mreže, evolucijski algoritmi, mehka logika in verjetnostni pristopi, strojno učenje, rudarjenje podatkov, sistemi na osnovi znanja; hibridni (mnogoteri) sistemi.

Umetna inteligenca:
Pregledno po knjigi Russel, Norvig:
1 uvod
2 inteligentni agenti
3 reševanje problemov s preiskovanjem
4 nadgradnja klasičnega iskanja
5 preiskovanja potez nasprotnikov
6 zadovoljevanje omejitev
7 logični agenti
8 logika prvega reda
9 sklepanje v logiki prvega reda
10 klasično planiranje
11 planiranje in delovanje v realnem svetu
12 predstavitev znanja
13 kvantificiranje verjetnosti
14 verjetnostno sklepanje
15 časovno verjetnostno sklepanje
16 preprosto odločanje
17 zapleteno odločanje
18 učenje s primeri
19 znanje in učenje
20 učenje verjetnostnih modelov
21 vzpodbujevalno učenje
22 procesiranje naravnega jezika
23 komunikacija v naravnem jeziku
24 zaznavanje
25 robotika
26 filozofske osnove
27 AI: sedanjost in bodočnost.

Inteligentni agenti: lastnosti, področja, prednosti in slabosti, trendi, primeri, taksonomija agentov, agentni jeziki in platforme, MAS, semantični Web in ontologije.

Globoke nevronske mreže: pregled.

Komunikacija človek-stroj: multimediji in komunikacija človek-stroj; komuniciranje preko gibov, govora, izrazov, hipermediji, inteligentni vmesniki, govorna forenzika, uporabniški profili, inteligentni asistenti, avatarji.

Kognitivne znanosti: pregled področja, kognitivna informatika, osnovne teze kognitivne informatike (Turingov test, Church-Turingova teza) in paradoksi (Searlova soba, Goedlov stavek), pregled računskih strojev od univerzalnih Turingovih dalje, superinteligenca.

Izzivi pri razvoju inteligentnih programskih sistemov: predstavitev celotnega procesa razvoja programskih projektov s poudarkom na reševanju problemov, na katere naletimo le pri večjih projektih.

Orodja in rešitve: pregled najboljših orodij in rešitev na trgu, predvsem generativne AI.

Scientific Method: scientific knowledge structures, scientific activities/processes.

Introduction: definitions of intelligent systems, artificial intelligence, agents.

Information society: overview, current state of the art, future directions, natural intelligent systems, intelligent services, computer intelligent systems, artificial intelligence, cognitive science.

Intelligent systems: properties, areas, advantages and disadvantages, trends, examples; single systems - expert systems, neural networks, evolutionary algorithms, fuzzy logic, machine learning, data mining, knowledge-based systems; hybrid (multiple) systems.

Artificial intelligence:
AI basic schoolbook (Russel and Norvig):
1 introduction
2 intelligent agents
3 solving problems by searching
4 beyond classical search
5 adversarial search
6 constraint satisfaction problems
7 logical agents
8 first-order logic
9 inference in first-order logic
10 classical planning
11 planning and acting in the real world
12 knowledge representation
13 quantifying uncertainty
14 probabilistic reasoning
15 probabilistic reasoning over time
16 making simple decisions
17 making complex decisions
18 learning from examples
19 knowledge in learning
20 learning probabilistic models
21 reinforcement learning
22 natural language processing
23 natural language for communication
24 perception
25 robotics
26 philosophical foundations
27 AI: the present and future.

Intelligent agents: properties, areas, overview, advantages and disadvantages, trends, examples, agent languages and platforms, MAS, semantic Web and ontologies.

Deep neural networks: a quick overview.

Communication human-computer: graphical user interfaces, speech synthesis and recognition, speech understanding, facial recognition, hypermedia, intelligent interfaces, forensic speech and audio analysis, user profiles.

Cognitive sciences: overview, cognitive informatics, basic theses of cognitive informatics (Turing test, Church-Turing thesis) and paradoxes (Searle room, Goedel statement), overview of computing mechanisms from the Universal Turing machine on, superintelligence.

Challenges at designing intelligent systems: the whole SW process of designing systems using artificial intelligence, intelligent systems and agents with the emphasis on specific approaches and dilemmas.

Tools and solutions: overview of tools and solutions, primarily generative AI.

Temeljna literatura in viri / Readings:

Izbrana poglavja iz naslednjih knjig: / Selected chapters from the following books:
S. Russel, and P. Norvig. Artificial Intelligence: A Modern Approach, 4th Edition. Pearson Education Limited, 2021. ISBN-13 978-0-13-461099-3
A.A. Hopgood. Intelligent Systems for Engineers and Scientists, 4th Edition. CRC Press, 2022. ISBN 978-1032126760
R. Sharda, D. Delen, and E. Turban. Business Intelligence and Analytics: Systems for Decision Support, 10th Edition. Prentice Hall, 2014. ISBN 978-0133050905.
D.L. Poole, and A.K. Mackworth. Artificial Intelligence: Foundations of Computational Agents. 3rd edition, Cambridge University Press, 2023. online.

Cilji in kompetence:
Objectives and competences:

Cilj predmeta je podati splošno znanje o umetni inteligenci, inteligentnih sistemih in inteligentnih agentih v povezavi s sorodnimi področji in informacijsko družbo. Uvodoma so predstavljeni osnovni koncepti omenjenih področij, cilji, motivacija, smisel, nameni in problemi pri uveljavljanju omenjenih metod.

Študenti, ki bodo uspešno končali ta predmet, bodo obvladali osnove inteligentnih sistemov in agentov in bodo usposobljeni za njihovo uporabo v reševanju zahtevnih problemov in vrednotenje njihovih rezultatov.

The goal of the course is to provide general and advanced knowledge of artificial intelligence, intelligent systems and intelligent agents in relation to the related fields and information society. In the introduction, basic concepts, goals, motivations and objectives are presented.

The students who will successfully complete this course will master the basics of intelligent systems and agents and will be capable of applying these systems in solving demanding problems and evaluating their results.

Predvideni študijski rezultati:
Intendeded learning outcomes:

Študenti bodo z uspešno opravljenimi obveznostmi tega predmeta pridobili:
- osnove znanstvenega pristopa in konceptov v umetni inteligenci, agentih in inteligentnih sistemih
- osnovna znanja umetne inteligence, agentov in inteligentnih sistemov
- pregled obstoječih nalog in metod
- obvladovanje tehničnih in praktičnih vidikov metod umetne inteligence in inteligentnih sistemov in agentov
- sposobnost uporabe obstoječih metod strojnega učenja in rudarjenja podatkov na novih problemih
- sposobnost ugotavljanja uspešnosti metod umetne inteligence, inteligentnih sistemov in agentov pri uporabi na konkretni nalogi

Students successfully completing this course will acquire:
- Basic scientific approach and concepts in artificial intelligence, agents and intelligent systems
- Basic knowledge about AI and intelligent systems and agents
- Overview of existing tasks and methods
- Getting acquainted with technical and practical aspects of AI, intelligent systems and agents
- The ability to apply existing ML and DM methods to problems
- The ability to identify whether ML or DM methods are successful given domain

Metode poučevanja in učenja:
Learning and teaching methods:

Predavanja, seminar, konzultacije, individualno delo.

Lectures, seminar, consultations, individual work.

Načini ocenjevanja:
Delež v % / Weight in %
Assesment:
Seminarska naloga
50 %
Seminar work
Ustni zagovor
50 %
Oral defense
Reference nosilca / Lecturer's references:
1. M. Gams, I. Yu-Hua Gu, A. Harma, A. Munos, V. Tam. Artificial intelligence and ambient intelligence. Journal of ambient intelligence and smart environments, ISSN 1876-1364, 2019, vol. 11, no. 1, str. 71-86, doi: 10.3233/AIS-180508.
2. R. Piltaver, M. Luštrek, S. Džeroski, M. Gjoreski, M. Gams. Learning comprehensible and accurate hybrid trees. Expert systems with applications, ISSN 0957-4174. 2021, vol. 164, str. 113980-1-113980-11, doi: 10.1016/j.eswa.2020.113980.
3. T. Kompara, J. Perš, D. Susič, M. Gams. A one-dimensional non-intrusive and privacy-preserving identification system for households. Electronics, ISSN 2079-9292, 2021, vol. 10, no. 5, str. 559-1- 559-21, doi: 10.3390/electronics10050559.
4. M. Gjoreski, A. Gradišek, B. Budna, M. Gams, G. Poglajen. Machine learning and end-to-end deep learning for the detection of chronic heart failure from heart sounds. IEEE access, ISSN 2169-3536, 2020, vol. 8, str. 20313-20324, doi: 10.1109/ACCESS.2020.2968900.
5. M. Gams, T. Kolenik. Relations between Electronics, Artificial Intelligence and Information Society through Information Society Rules, Electronics 2021, 10(4), MDPI, DOI 10.3390/electronics10040514