Yoshua Bengio

Hidden sampling biases inflate performance in gene regulatory network inference

The paper shows that sampling biases in negative regulatory interactions inflate performance in gene regulatory network inference and proposes a degree-aware sampling approach to address this issue.

A neuronal least-action principle for real-time learning in cortical circuits

The paper introduces a neuronal least-action principle to model real-time learning in cortical circuits by minimizing voltage dynamics and error correction.

A high-throughput phenotypic screen combined with an ultra-large-scale deep learning-based virtual screening reveals novel scaffolds of antibacterial compounds

This study combines high-throughput screening with deep learning to identify novel antibacterial compounds, achieving a 90X higher hit rate than traditional methods.

Learning from unexpected events in the neocortical microcircuit

The paper shows that cortical pyramidal neurons exhibit distinct unexpected event signals in somata and distal apical dendrites that change over days, suggesting a role in hierarchical computation.

Training neural networks to recognize speech increased their correspondence to the human auditory pathway but did not yield a shared hierarchy of acoustic features

This paper compares CNN speech recognition layers to human auditory fMRI activity and finds no shared acoustic feature hierarchy, with all regions most similar to the first fully-connected layer.

CAMAP: Artificial neural networks unveil the role of codon arrangement in modulating MHC-I peptides presentation

The paper introduces CAMAP, an artificial neural network that predicts MHC-I peptide presentation by analyzing codon arrangement in mRNA sequences, improving prediction accuracy beyond traditional methods.

BigBrain 3D atlas of cortical layers: cortical and laminar thickness gradients diverge in sensory and motor cortices

The paper presents a 3D laminar atlas of the human cerebral cortex using a convolutional neural network and uses it to analyze thickness gradients in sensory and motor cortices.