Learning algorithms in neural networks and emerging collective properties of agent based models

• Grant number: 19/01368-8
• Support Opportunities: Scholarships in Brazil - Scientific Initiation
• Start date: May 01, 2019
• End date: July 31, 2021
• Field of knowledge: Physical Sciences and Mathematics - Physics - Classical Areas of Phenomenology and Applications
• Principal Investigator: Nestor Felipe Caticha Alfonso
• Grantee: Pietro Zanin
• Host Institution: Instituto de Física (IF). Universidade de São Paulo (USP). São Paulo , SP, Brazil

Abstract

The student will engage in an ongoing research program that deals with (I) learning in Neural Networks and (II) the construction and analysis of agent based models that process information using neural networks. The theoretical background includes Probability theory, Statistical Mechanics, Information theory and Machine Learning. The methods include analytical and computational techniques. Applications to consensus formation with respect to moral opinions and to the study of opinion dynamics. The student will compare machines learning with different learning algorithms e compare theoretical predictions to large data bamks about moral opinions, ethnographic data and voting patterns in legislative houses from different countries.