User profiles for Rodrigo Echeveste
Rodrigo EchevesteResearch Institute for Signals, Systems and Computational Intelligence sinc(i) (FICH-UNL … Verified email at sinc.unl.edu.ar Cited by 376 |
Cortical-like dynamics in recurrent circuits optimized for sampling-based probabilistic inference
Sensory cortices display a suite of ubiquitous dynamical features, such as ongoing noise
variability, transient overshoots and oscillations, that have so far escaped a common, principled …
variability, transient overshoots and oscillations, that have so far escaped a common, principled …
Domain generalization via gradient surgery
In real-life applications, machine learning models often face scenarios where there is a
change in data distribution between training and test domains. When the aim is to make …
change in data distribution between training and test domains. When the aim is to make …
[HTML][HTML] Addressing fairness in artificial intelligence for medical imaging
A plethora of work has shown that AI systems can systematically and unfairly be biased against
certain populations in multiple scenarios. The field of medical imaging, where AI systems …
certain populations in multiple scenarios. The field of medical imaging, where AI systems …
[HTML][HTML] Generating functionals for computational intelligence: the Fisher information as an objective function for self-limiting Hebbian learning rules
R Echeveste, C Gros - Frontiers in Robotics and AI, 2014 - frontiersin.org
Generating functionals may guide the evolution of a dynamical system and constitute a
possible route for handling the complexity of neural networks as relevant for computational …
possible route for handling the complexity of neural networks as relevant for computational …
[HTML][HTML] Energetic substrate availability regulates synchronous activity in an excitatory neural network
Neural networks are required to meet significant metabolic demands associated with performing
sophisticated computational tasks in the brain. The necessity for efficient transmission of …
sophisticated computational tasks in the brain. The necessity for efficient transmission of …
Towards unraveling calibration biases in medical image analysis
In recent years the development of artificial intelligence (AI) for medical image analysis has
gained enormous momentum. At the same time, a large body of work has shown that AI …
gained enormous momentum. At the same time, a large body of work has shown that AI …
[HTML][HTML] The redemption of noise: Inference with neural populations
R Echeveste, M Lengyel - Trends in neurosciences, 2018 - cell.com
In 2006, Ma et al. presented an elegant theory for how populations of neurons might
represent uncertainty to perform Bayesian inference. Critically, according to this theory, neural …
represent uncertainty to perform Bayesian inference. Critically, according to this theory, neural …
[HTML][HTML] EI balance emerges naturally from continuous Hebbian learning in autonomous neural networks
P Trapp, R Echeveste, C Gros - Scientific reports, 2018 - nature.com
Spontaneous brain activity is characterized in part by a balanced asynchronous chaotic
state. Cortical recordings show that excitatory (E) and inhibitory (I) drivings in the EI balanced …
state. Cortical recordings show that excitatory (E) and inhibitory (I) drivings in the EI balanced …
Two-trace model for spike-timing-dependent synaptic plasticity
R Echeveste, C Gros - Neural computation, 2015 - direct.mit.edu
We present an effective model for timing-dependent synaptic plasticity (STDP) in terms of
two interacting traces, corresponding to the fraction of activated NMDA receptors and the …
two interacting traces, corresponding to the fraction of activated NMDA receptors and the …
Bridging physiological and perceptual views of autism by means of sampling-based Bayesian inference
Theories for autism spectrum disorder (ASD) have been formulated at different levels, ranging
from physiological observations to perceptual and behavioral descriptions. Understanding …
from physiological observations to perceptual and behavioral descriptions. Understanding …