Y
Yoshua Bengio
Researcher at Université de Montréal
Publications - 1146
Citations - 534376
Yoshua Bengio is an academic researcher from Université de Montréal. The author has contributed to research in topics: Artificial neural network & Deep learning. The author has an hindex of 202, co-authored 1033 publications receiving 420313 citations. Previous affiliations of Yoshua Bengio include McGill University & Centre de Recherches Mathématiques.
Papers
More filters
Posted Content
Dendritic cortical microcircuits approximate the backpropagation algorithm
TL;DR: In this paper, the authors introduce a multilayer neural network model with simplified dendritic compartments in which error-driven synaptic plasticity adapts the network towards a global desired output.
Proceedings Article
The Causal-Neural Connection: Expressiveness, Learnability, and Inference
TL;DR: In this paper, the authors show that the causal hierarchy theorem (Thm. 1, Bareinboim et al., 2020), which describes the limits of what can be learned from data, still holds for neural models.
Posted Content
Learning the Arrow of Time
TL;DR: It is illustrated how a learned arrow of time can capture meaningful information about the environment, which in turn can be used to measure reachability, detect side-effects and to obtain an intrinsic reward signal.
Proceedings Article
Bounding the Test Log-Likelihood of Generative Models
TL;DR: In this paper, a non-parametric density estimator of the model's probability function from samples generated by the model is proposed and proved to provide a lower bound on the true test log-likelihood, and an unbiased estimator as the number of generated samples goes to infinity.
Combining Model-based and Model-free RL via Multi-step Control Variates
TL;DR: The authors leverage multi-step neural network based predictive models by embedding real trajectories into imaginary rollouts of the model, and use the imaginary cumulative rewards as control variates for model-free algorithms.