I work at the interphase between computational neuroscience and machine learning, bringing in tools from complex systems, information theory and statistics, to try to understand how the brain acquires, stores, and processes information. To do so, I employ both analytic methods and numerical simulations/optimization.
My research interests include synaptic plasticity rules, both derived from objective functions (top-down) and in terms of their biological underpinnings (bottom-up).
My recent work has focused on how the brain could encode and deal with uncertainty, training biologically plausible neural networks to perform sampling-based probabilistic inference.
I am currently working to develop quantitative tools based on graph convolutional neural networks to aid in the diagnosis of autistic spectrum disorders.
Dealing with uncertainty with probabilistic sampling
Dr. Rodrigo Echeveste
Santa Fe, Argentina
Ciudad Universitaria UNL,
Ruta Nacional Nº 168, km 472.4,
FICH, 4to Piso (3000) Santa Fe – Argentina