Skip to main content

Dr. Marko Puljic

Photo Coming Soon
Title:
Adjunct Professor
Phone:
901.848.2313
Bio:

Education:
PhD Computer Science, University of Memphis, 2005
MBA Finance, University of Memphis, 1998
BS Mathematics, University of Zagreb, 1996

Bio:
Research of professor Marko Puljic focuses on developing novel artificial intelligent system motivated by the operation of brains and the study of brain-like computing that operates through chaotic dynamical system or chaotic dynamical memories. At CLION Lab and AI Lab at Amherst, Marko conducted research on neural networks, machine learning, knowledge acquisition, computational neuroscience, and neurally-inspired computing  for processing of big data for the brain-computer interfaces and autonomous decision support systems. Professor's greatest personal interest are visiting the sources of fresh water sources in America.

Publications/Presentations/Lectures:
Robert Kozma and Marko Puljic. Neural population dynamics modeled by mean-field graphs. In Numerical Analysis and Applied Mathematics ICNAAM, volume 1389, pages 1348– 1352, 2011.
Robert Kozma and Marko Puljic. Hierarchical random cellular neural networks for system-level brain-like signal processing. Neural Networks, 2013.
Robert Kozma and Marko Puljic. Pattern-based computing via sequential phase transitions in hierarchical mean field neuropercolation. Theoretical Computer Science, 2015.
Robert Kozma and Marko Puljic. Random graph theory and neuropercolation for modeling brain oscillations at criticality. Current opinion in neurobiology, 31:181–188, 2015.
Robert Kozma and Marko Puljic. Pattern-based computing via sequential phase transitions in hierarchical mean field neuropercolation. Theoretical Computer Science, 633:54–70, 2016.
Robert Kozma, Marko Puljic, and Walter Freeman. Thermodynamic model of criticality in the cortex based on eeg/ecog data. arXiv:1206.1108v1, 2012.
Robert Kozma, Marko Puljic, and Walter J Freeman. Thermodynamic model of criticality in the cortex based on eeg/ecog data. Criticality in Neural Systems, pages 153–176, 2014.
Robert Kozma, Yury Sokolov, Marko Puljic, Sanquing Hu, and Miklós Ruszinkó. Modeling learning and strategy formation as phase transitions in cortical networks. In Systems, Man, and Cybernetics (SMC), 2016 IEEE International Conference on, pages 004099–004105. IEEE, 2016.

Link: computorica.com