Impact of varying neighbourhood size in LLNA's rule space exploration by stochastic gradient descent

• Grant number: 24/16345-1
• Support Opportunities: Scholarships abroad - Research Internship - Master's degree
• Start date: September 30, 2024
• End date: December 29, 2024
• Field of knowledge: Physical Sciences and Mathematics - Computer Science
• Principal Investigator: Odemir Martinez Bruno
• Grantee: Lucas Caldeira de Oliveira
• Supervisor: Jan Marcel Baetens
• Host Institution: Instituto de Física de São Carlos (IFSC). Universidade de São Paulo (USP). São Carlos , SP, Brazil
• Institution abroad: Ghent University (UGent), Belgium
• Associated to the scholarship: 24/02727-0 - Differentiable network automaton for gradient descent optimization, BP.MS

Abstract

The objective of this project is to train the candidate in the analysis of cellular automata for networks (i.e. network automata, NAs). The project will be developed in the research group of Prof. Dr. Jan M. Baetens, installed at Ghent University. In this research group, the candidate will implement a rule space exploration approach based on stochastic gradient descent, and analyze the effect of the rule resolution in finding an optimal Life-Like Network Automata (LLNA) rule encoding for synthetic datasets. The knowledge acquired by the candidate during the project in Belgium will serve to advance the research project related to the fellowship in Brazil.