Ponedeljkov seminar računalništva in informatike - Arhiv
2024 | 2023 | 2022 | 2021 | 2020 | 2019 | 2018 | 2017 | 2016 | 2015 | 2014 | 2013 | 2012 |
1 | 2 | 3 | 4 | 5 | 6 | 7 | 8 | 9 | 10 | 11 | 12 |
nedelja, 26. november 2023 Vanja MILESKI: A ResNet Convolutional Neural Network for Time Series data using InceptionNet paradigms
V ponedeljek, 27. novembra 2023, bo ob 16.00 uri izvedeno predavanje v okviru PONEDELJKOVEGA SEMINARJA RAČUNALNIŠTVA IN INFORMATIKE Oddelkov za Informacijske znanosti in tehnologije UP FAMNIT in UP IAM.
ČAS/PROSTOR: 27. november 2023 ob 16.00 prek Zoom-a.
----------------------------------------
PREDAVATELJ: Vanja MILESKI
----------------------------------------
After graduating from the Faculty of Computer and Information Science at the University of Ljubljana in 2015, Vanja Mileski started working at the Jožef Stefan Institute (JSI). He was a Master's student at the International Postgraduate School Jožef Stefan and a student researcher at the JSI. After finishing his Master's studies, he applied his knowledge of data mining in the private sector as a Data Scientist in the retail, telecommunications, banking, stock market and insurance sectors.
His current research interests include time-series classification, deep learning, ResNet and Inception architectures.
-----------------------------------------------------------------------------------------------------------------------------------------
NASLOV: A ResNet Convolutional Neural Network for Time Series data using InceptionNet paradigms
-----------------------------------------------------------------------------------------------------------------------------------------
POVZETEK:
The recent progress in Convolutional Neural Network (CNN) designs has extended their effectiveness to time series data as well. Time series features, which can be represented as one-dimensional vectors, open the door for training deeper networks using ResNet-inspired structures. Inception modules provide the capability to the network to handle objects and patterns of different sizes and capture both local details and global context. We propose an Inception-Residual CNN model tailored for time series data which will be applied on real-life data in retail.
Seminar bo potekal v angleškem jeziku prek Zoom-a s pričetkom ob 16:00 uri.
Povezava:
https://upr-si.zoom.us/j/297328207?pwd=S3Zpdk1VR3pjckNtWkQwKzlvcDR5UT09
Meeting ID: 297 328 207
Passcode: 123456789
Vabljeni.
petek, 10. november 2023 Ivan Luković: Organizational Capability for Information Management – Do we Feel a Big Data Crisis?
V ponedeljek, 13. november 2023, bo ob 16.00 uri izvedeno
predavanje v okviru PONEDELJKOVEGA SEMINARJA RAČUNALNIŠTVA IN INFORMATIKE
Oddelkov za Informacijske znanosti in tehnologije UP FAMNIT in UP IAM.
ČAS/PROSTOR: 13. november 2023 ob 16.00 v FAMNIT-VP3.
-------------------------------------------------------------------
PREDAVATELJ: Ivan LUKOVIĆ
-------------------------------------------------------------------
Ivan Luković received his Ph.D. at the University of Novi Sad, Faculty of Technical Sciences in 1996. Currently, he works as a Full Professor at the Faculty of Organizational Sciences of the University of Belgrade, where he lectures in several Computer Science and Informatics courses. His research interests are related to Database Systems, Business Intelligence, Software Engineering, and Data Science. He is the author or co-author of over 200 papers, 4 books, and 30 industry projects and software solutions in the area. He supervised 12 completed Ph.D. theses. He created a new set of B.Sc. and M.Sc. study programs in Information Engineering, i.e. Data Science, at the Faculty of Technical Sciences. The programs were accredited the first time in 2015. Currently, he is a chair of Managing Board of the Computer Science and Information Systems (ComSIS) journal, and a chair of M.Sc. study program in Information Engineering at Faculty of Organizational Sciences. He is also a member of Serbian AI Society.
-------------------------------------------------------------------------------------------
NASLOV: Organizational Capability for Information Management – Do we Feel a Big Data Crisis?
-------------------------------------------------------------------------------------------
POVZETEK: Nowadays, modern business includes acquisition and storing enormous data volumes, larger than ever before. Most often, collected data are used in a shorter time frame, and then they are archived and almost not used, effectively. On the other hand, such data represent a significant value that a company can utilize so as to reach created goals and provide a sustainable development. Unfortunately, a daily practice in many companies still intensively points out to the problem of a serious gap between the identified needs for knowledge, on one hand, and inability of modern software products to address such needs in an effective way, on the other hand. Despite that massive data volumes already exist and that modern information solutions provide the excellent technology prerequisites for a development and industry implementation of high quality software applications. We can call such a phenomenon a “big data crisis”. Some of important causes of the aforementioned phenomenon are in the following: (1) Unsatisfactory level of organization maturity in regard to the: capabilities for information management, quality management, and business processes; (2) Unsatisfactory level of accumulated knowledge in a problem domain; and (3) Unsatisfactory level of accumulated knowledge in a domain of software engineering, particularly in a domain of the development and formal specification of models for software products aimed at generation of company knowledge and decision support. Alleviating the aforementioned phenomenon is a strategic and long term task, possible by simultaneous addressing all its significant causes, only.
In this talk, some of the author's research and educational efforts will be presented, trying to address the most influencing factors for information management and innovations, leading to the digital transformation process.
Seminar bo potekal v angleškem jeziku v predavalnici FAMNIT-VP3 s pričetkom ob 16:00 uri.
Vabljeni.
ponedeljek, 6. november 2023 Uroš SERGAŠ & Jar Žiga MARUŠIČ: The AI alignment problem and its implications for society
V ponedeljek, 6. novembra 2023, bo ob 16.00 uri izvedeno
predavanje v okviru PONEDELJKOVEGA SEMINARJA RAČUNALNIŠTVA IN INFORMATIKE
Oddelkov za Informacijske znanosti in tehnologije UP FAMNIT in UP IAM.
ČAS/PROSTOR: 6. november 2023 ob 16.00 v FAMNIT-VP2.
-------------------------------------------------------------------
PREDAVATELJA: Uroš SERGAŠ & Jar Žiga MARUŠIČ
-------------------------------------------------------------------
Uroš Sergaš is a PhD student in Computer Science at UP FAMNIT, Jar Žiga Marušič is a PhD student in Philosophy at UL FF. Both are also teaching assistants at UP FAMNIT, Uroš in the Department of Information Sciences and Technologies, Jar in the Department of Psychology. Together they are interested in the implications and uses of artificial intelligence in society. Over the summer they researched the AI alignment problem.
-------------------------------------------------------------------------------------------
NASLOV: The AI alignment problem and its implications for society
-------------------------------------------------------------------------------------------
POVZETEK:
Humanity has again found itself on the brink of a new era, as large language models (LLM) seem poised to bring about important social changes. As these models advance in complexity, the issue of AI alignment is gaining popularity in a daily conversation topic.
This research explores two contrasting viewpoints on the AI alignment problem: the Orthogonalist perspective pioneered by Nick Bostrom and the Anti-orthogonalist critique formulated by Nick Land. The former posits that an AI’s goals are independent of its intelligence, suggesting that a "friendly AI" (fully aligned to human values) is possible. The latter challenges its separation of intelligence and values from the perspective that intelligence increase leads to a greater ability for self-reflection, ultimately leading to a restructuring of its value structure to prioritize further cognitive enhancement. We discuss the implications of these ideas and highlight the current patterns seen in the developments of widely available AI tools, such as LLM.
Seminar bo potekal v angleškem jeziku v predavalnici FAMNIT-VP2 s pričetkom ob 16:00 uri.
Vabljeni.