Bio

Petra Povalej graduated from the University of Maribor, in Slovenia. She is currently working as a research assistant in the Laboratory for System Design in the Faculty of Electrical Engineering and Computer Science, University of Maribor. At the same time, she is finishing her Ph.D. in machine learning using cellular automata. Her interests include machine learning, multi-agent systems, and decision support.

Project: Machine Learning

A large variety of problems arising in engineering, physics, chemistry, medicine, and economics can be formulated as classification problems. Although classification represents only a small part of the machine learning field, there are many methods available. The goal of our project is to explore the “world” of possible nested functions for finding the one that most accurately approximates the data. Results of the conducted experiments have shown that this approach can produce comparable results to other often-used methods. However, more experiments will be conducted with different initial parameters, and then we will be able to make more precise conclusions.

Favorite Four-Color, Nearest-Neighbor, Totalistic Rule

Rule chosen: 629 starting from {1,0,0,0,1,0,3,2,2}