MISANU

PROGRAM

Plan rada Seminara iz veštačke inteligencije za DECEMBAR 2021.

Registraciona forma za učesće, i link na predavanje ako ste već registrovani:
https://miteam.mi.sanu.ac.rs/asset/CW5nJWDSEZDj7p32p
Ukoliko želite samo da gledate predavanje bez mogućnosti aktivnog učešća, prenos će biti dostupan na:
https://miteam.mi.sanu.ac.rs/asset/4LNW8WtML7rLKojoz
Na ovom linku se mogu pronaci kratka uputstva na srpskom i engleskom:
https://miteam.mi.sanu.ac.rs/asset/Kc7qJtEvoMFx9MFnz

SREDA, 01.12.2021. u 19:00, Online
Sang-Wook Kim, Department of Computer Science & Engineering, Hanyang University, Seoul, Korea
RECOMMENDATION SYSTEMS: CONCEPTS, TECHNIQUES, AND APPLICATIONS
As the number of online items such as products, contents, and people significantly grows these days, it becomes a difficult task for users to find the items on their own. Good matching of users to their suitable items is very important to enhance users' satisfaction and companies' profit, which highlights the necessity of recommendation systems technology. The recommendation system analyzes the characteristics of users' past behaviors, predicting the items with which individual users would be truly satisfied. In this talk, we discuss the concepts, techniques, and applications of recommendation systems. We start with the concepts of recommendation systems and introduce real-world applications in a variety of business fields. Then, we explain three categories of approaches to recommendation systems: content-based, collaborative-filtering-based, and trust-based approaches. Next, we describe machine learning techniques widely applied in developing recommendation systems. Finally, we share the state-of-the-art techniques developed in our group and show their effectiveness and efficiency with evaluation results. The agenda of this talk is organized as follows.

SREDA, 08.12.2021. u 19:00, Online
Esko Turunen, Tampere University, Finland
THE GUHA METHOD - LOGIC APPROACH TO DATA MINING
GUHA (Generalized Unary Hypothesis Automata) is a method of exploratory data analysis i.e., data mining. Its development started in the 1960s and is still developing rapidly. GUHA is based on a particular logic formalism: in the scope there are unary predicates combined by logic connectives and generalized quantifiers, whose models are finite. The truth of closed sentences is defined in a very special but natural way. GUHA logic satisfies the soundness and completeness Theorems. There is also a related software implementation called LISpMiner. Data Mining LISpMiner with software is not a 'black box' method, but the user asks analytical questions to which the software seeks answers. We briefly introduce GUHA theory and, if time allows, also a practical application.

SREDA, 15.12.2021. u 19:00, Online
Aleksandra Dedinec, Faculty of Computer Science and Engineerings, Ss. Cyril and Methodius University, Skopje, Macedonia
APPLICATION OF MACHINE LEARNING MODELS IN SMART GRIDS
In this research, application of machine learning methods in smart grids is analyzed. This aspect includes the utilization of the large amount of available digital information for creating smart models for planning and forecasting. The latest and new achievements in the field of machine learning are used for that purpose. Specifically, models based on deep belief networks are developed and it is examined whether these models may be applied for electricity load and price forecasting. For that purpose, the hourly data of the prices of the power exchanges in the region of Southeast Europe (Serbia, Bulgaria and Croatia) are used, as well as hourly data for electricity load in Macedonia. The obtained results present the advantages of the developed models based on deep belief networks, compared to the traditional neural networks, when applied to electricity price and load forecasting. Additionally, the important variables that are used as an input in each of the models are presented.

SREDA, 22.12.2021. u 19:00, Online
Dušan Surla, Univerzitet u Novom Sadu
ZASTUPLJENOST OBLASTI VEŠTAČKE INTELIGENCIJE NA DOKTORSKIM AKADEMSKIM STUDIJAMA U REPUBLICI SRBIJI
Doktorske studije se organizuju na nivou fakulteta a mogu se organizovati i na nivou Univerziteta. Analizirane su samo naučne oblasti Računarske nauke (obrazovno-naučno polje Prirodno-matematičke nauke) i Elektrotehničko i računarsko inženjerstvo (obrazovno-naučno polja Tehničko-tehnološke nauke). Dat je osvrt i na formalno pravne mogućnosti organizovanja doktorskih studija.
Кonstatovano je da na svim državnim i privatnim univerzitetima i fakultetima postoji oko 20 (dvadeset) programa doktorskih studija u kojima postoje predmeti iz oblasti veštačke inteligencije. Na predavanju će biti opisana postojeća organizacija doktorskih studija i zastupljenost predmeta iz oblasti veštačke inteligencije. Biće razmatrani različiti oblici organizacije doktorskih studija na nivou više fakulteta, na nivou više univerziteta i međunarodne doktorske studije.

SREDA, 29.12.2021. u 19:00, Online
Više autora
SASTANAK AI SEMINARA POSVEĆEN TERMINOLOGIJI IZ VEŠTAČKE INTELIGENCIJE NA SRPSKOM JEZIKU
Uvodničari (po azbučnom redu):
dr Staša Vujičić Stanković, docent, Matematički fakultet Beograd
dr Tatjana Davidović, naučni savetnik, Matematički institut SANU Beograd
Tanja Dinić, profesorka francuskog jezika, Saobraćajni fakultet Beograd
dr Ulfeta Marovac, docent, Univerzitet u Novom Pazaru
dr Ranka Stanković, vanredni profesor, Rudarsko-geološki fakultet Beograd
Zoran Čikić, profesor engleskog jezika i sudski prevodilac za engleski jezik, Hemofarm, Beograd
dr Branimir Šešelja, redovni profesor u penziji. Prirodno matematički fakultet Novi Sad
dr Gordana Štasni, redovni profesor, Filozofski fakultet Novi Sad
Na kraju sastanka organizovaće se i razgovor o nastavku AI inicijative.

Ovaj onlajn seminar nastao je kao nastavak sastanka “Serbian AI Meeting” i zamišljen je da na njemu istraživači iz Srbije i iz dijaspore, kao i istraživači sa univerzteta, naučnih instituta i iz prakse predstavljaju naučne teme i rezultate iz oblasti veštačke inteligencije.
Link za svako pojedinačno predavanje biće dostavljen dan pre održavanja predavanja.

Andreja Tepavčević
Rukovodilac seminara