Luciano Dyballa

Luciano Dyballa is an Assistant Professor at IE University since 2024. He obtained his Ph.D. in Computer Science from Yale University under the supervision of Steven Zucker, focusing on machine learning, computer vision, and computational neuroscience. He was then awarded a Swartz Postdoctoral Fellowship to continue his work on manifold inference applied to neural networks, during which he maintained collaborations with renowned groups at UCSF (Stryker Lab), UCLA (Field Lab), and UMass (Yemini Lab). Prior to Yale, he obtained a B.S. in Chemical Engineering and an M.S. in Computer Science, both from the Federal University of Rio de Janeiro, in Brazil. He has also worked as an engineer, performing process optimization and developing software for data mining and natural language processing.

Dr. Dyballa is interested in investigating the mechanisms and principles behind real and artificial intelligence, and in bridging the gap between biological and deep neural networks. He has published in academic journals such as Proceedings of the National Academy of Sciences and Neural Computation, and has presented his work at various meetings and conferences within the fields of computational neuroscience (COSYNE, SfN, NAISys), computer vision (VSS, MODVIS), and artificial intelligence (ICLR).

Corporate Experience

• Process Engineer, Petrobras, Brazil, 2009 - 2013

Academic Experience

• Assistant Professor at IE University, 2024 - Present

• Postdoctoral Associate, Yale University, USA, 2021 - 2024

• Teaching Fellow, Yale University, USA, 2016 - 2020

Academic Background

• Ph.D. in Computer Science, Yale University, USA, 2021

• M.S. in Computer Science, Yale University, USA, 2018

• M.S. in Computer Science, Federal University of Rio de Janeiro, Brazil, 2015

• B.S. in Chemical Engineering, Federal University of Rio de Janeiro, Brazil, 2008

Selected Publications

• Dyballa, L., Lang, S., Haslung-Gourley, A., Yemini, E., Zucker, S. (2024). “Learning dynamic representations of the functional connectome in neurobiological networks”, The Twelfth International Conference on Learning Representations (ICLR 2024)

• Dyballa, L., Rudzite, A., Hoseini, M., Thapa, M., Stryker, M., Field, G., Zucker, S. (2024). “Population encoding of stimulus features along the visual hierarchy”, Proceedings of the National Academy of Sciences, 121(4): e2317773121

• Dyballa, L., Zucker, S. (2023). “IAN: Iterated Adaptive Neighborhoods for manifold learning and dimensionality estimation”, Neural Computation, 35 (3): 453–524