Yoshua Bengio

TL;DR: This paper systematically study the differences introduced by distinct receptive field enlargement methods and their impact on the performance of a novel architecture, called Fully Convolutional DenseResNet (FC-DRN), and reports state-of-the-art result on the Camvid dataset.

TL;DR: The article discusses artificial intelligence and the machine learning known as deep learning, referencing the history of AI from the 1950s through the mid 2010s and the algorithms used in deep learning.

TL;DR: In this article, a two-phase learning procedure for fixed point recurrent networks is presented, where neurons perform leaky integration and synaptic weights are updated through a local mechanism, and the algorithm does not compute the true gradient of the objective function, but rather approximates it at a precision which is proven to be directly related to the degree of symmetry of the feedforward and feedback weights.

TL;DR: Methods that can be deployed to a smartphone to locally and proactively predict an individual's infectiousness based on their contact history and other information are developed, suggesting PCT could help in safe re-opening and second-wave prevention.

TL;DR: It is proved that, if the true latent maps to the observed high-dimensional data via a polynomial function, then representation learning via minimizing standard reconstruction loss (used in autoencoders) can identify the true latents up to affine transformation.