Assistant Professor Bruno Ribeiro Receives CAREER Award

05-20-2020

We live in a world where social networking applications can make uncanny friend suggestions, food delivery robots know how to safely cross streets, and a coronavirus vaccine will be more rapidly developed because of AI guided algorithms. Assistant professor Bruno Ribeiro, of the Department of Computer Science, has received a National Science Foundation CAREER Award to further develop the tools application developers use to build such systems in simpler and provably accurate ways.

Given that theoretical understanding of the mathematical abstractions of graphs and tensors has so significantly advanced in the past century, the opportunity now exists for the development of practical tools for day-to-day machine learning tasks. Ribeiro’s research aims to make available new representations to neural network architectures that are both sufficiently expressive for complex tasks and computationally tractable for greater deployment.

Ribeiro remarks, “This project uses prior work into a novel blueprint for better modeling complex relational input data, thereby translating the modern theoretical interpretation of sets, graphs, tensors, and logical formulae into provably more capable practical tools.”

The key insight of this project is to leverage invariant theory to develop a novel framework for representation learning of complex relational data via approximate invariances. Ribeiro feels the full development of the framework in his project holds promise to harness the synergy between invariant theory and computational methods.

CAREER awards are the National Science Foundation’s most prestigious awards given to junior faculty who embody the role of teacher-scholars through research, education and the integration of those concepts within the mission of their organizations. NSF CAREER awards support promising and talented researchers in building a foundation for a lifetime of leadership. Receiving this award reflects this project’s merit of the NSF statutory mission and its worthiness of financial support.

Ribeiro’s projected is entitled, “A Novel Blueprint for Representation Learning of Relational Invariances.”

 

Writer: Emily Kinsell, emily@purdue.edu

Source: Bruno Ribeiro, ribeirob@purdue.edu