Vice Rector for International Relations, Singidunum University, Serbia
Head of the Department of Mathematical Sciences, State University of Novi Pazar, Serbia

Biography: Milan Tuba is Vice Rector for International Relations, Singidunum University, Belgrade, Serbia and the Head of the Department for Mathematical Sciences at State University of Novi Pazar. He received B. S. in Mathematics, M. S. in Mathematics, M. S. in Computer Science, M. Ph. in Computer Science, Ph. D. in Computer Science from University of Belgrade and New York University. From 1983 to 1994 he was in the U.S.A. first as a graduate student and teaching and research assistant at Vanderbilt University in Nashville and Courant Institute of Mathematical Sciences, New York University and later as Assistant Professor of Electrical Engineering at Cooper Union School of Engineering, New York. During that time he was the founder and director of Microprocessor Lab and VLSI Lab, leader of scientific projects and theses supervisor. From 1994 he was Assistant Professor of Computer Science and Director of Computer Center at University of Belgrade, from 2001 Associate Professor, Faculty of Mathematics, University of Belgrade, from 2004 also a Professor of Computer Science and Dean of the College of Computer Science, Megatrend University Belgrade and from 2014 Dean of the Graduate School of Computer Science at John Naisbitt University. He was teaching more than 20 graduate and undergraduate courses, from VLSI Design and Computer Architecture to Computer Networks, Operating Systems, Image Processing, Calculus and Queuing Theory. His research interest includes heuristic optimizations applied to computer networks, image processing and combinatorial problems. Prof. Tuba is the author or coauthor of more than 200 scientific papers and coeditor or member of the editorial board or scientific committee of number of scientific journals and conferences. Member of the ACM, IEEE, AMS, SIAM, IFNA.

References in the last 5 years:
• More than 20 papers published in journals with impact factor, indexed in Thomson Reuters (Clarivate Analytics)
• Over 35 chapters in Springer, Elsevier and IFSA books
• Over 35 invited keynote and plenary lectures at international conferences
• Participated and published papers at more than 100 international conferences indexed in WoS, Scopus, IEEE Xplore, Australian CORE list.

Over 200 papers registred in Google Scholar with more than 2,500 citations and h-index 27 and g-index 43.
https://scholar.google.com/citations?user=lQQCeKIAAAAJ&hl=en&oi=ao

Speech Title: Swarm Intelligence applied to Machine Learning

Abstract: Machine learning is a relatively new and very important scientific field that studies algorithms used to execute certain task without being explicitly programmed. Machine learning methods build models based on the sample data that search for patterns that will enable autonomous predictions or decisions when new unknown data are presented. Nowadays, machine learning methods are used in countless areas including economy, biology, medicine, autonomous vehicles, security, and many more. All methods can be divided into three main categories based on the training process: supervised, unsupervised and reinforcement learning. Some of the well-known machine problem tasks are classification, regression, clustering, etc. Due to the extensive need for machine learning in numerous fields, many different methods for solving different tasks were proposed. Support vector machines, artificial neural networks, decision trees and forests were successfully used for solving different classification problems while some of the well-known clustering algorithms include k-means and k-nearest neighbors. The problem with all these methods is that in order to achieve the best possible results, some parameters need to be tuned (e.g. soft margin parameter in support vector machine, initial cluster centers in k-means, activation function, number of hidden layers and nodes in deep artificial neural networks, etc.). Machine learning parameter tuning is usually a hard optimization problem and it cannot be solved by deterministic methods such as exhaustive search (at least not in a reasonable time frame). For such problems, stochastic population search algorithms, such as nature-inspired algorithms, especially swarm intelligence, were studied and successfully applied. In this talk some applications of the swarm intelligence algorithms to hard optimization problems in machine learning will be presented.