Bruno Iochins Grisci
Computer Science
What if teaching a neural network to learn actually changes the way it processes information? This fundamental question guides the research of Bruno Grisci, a professor of artificial intelligence at the Federal University of Rio Grande do Sul. He explores how learning methods may shape the reasoning of neural networks, with the potential to develop systems that are more trustworthy, transparent, and aligned with human values.
He holds bachelor’s, master’s, and doctoral degrees in computer science from the Federal University of Rio Grande do Sul (UFRGS) and has conducted research in the United Kingdom, Chile, Germany, and Canada. He has received the AB3C Young Bioinformatician Award and an honorable mention from the CAPES Thesis Award. He was also selected to participate in the prestigious Heidelberg Laureate Forum alongside 200 other young scientists.
Beyond computers and algorithms, Grisci is passionate about art and pop culture. He has worked as a film and comic book columnist, written fiction, and pursued photography as a creative outlet. Inspired by his mother, a psychologist and university professor, from an early age, he values deep, thoughtful inquiry and finds joy in animated films.
Projects
Modern artificial neural networks are fundamental to technologies that recognize images, interpret language, and support automated decision-making. But how do these systems actually learn? This project investigates whether different training strategies, including traditional gradient-based optimization and algorithms inspired by evolutionary processes, enable networks to develop distinct forms of “reasoning” and “behavior.” Through carefully controlled experiments and interpretability techniques, we analyze the internal workings of these models to uncover what occurs inside the “black box.” Our primary objective is to determine whether and how the choice of training method impacts the performance and behavioral characteristics of neural networks. Insights from this work could inform the design of more dependable, transparent, and human values-aligned artificial intelligence systems.
Amount invested
Institutions
- Universidade Federal do Rio Grande do Sul
