activity
20122021
most citedDendritic error backpropagation in deep cortical microcircuits

38 citations · 84 across the 6 of their papers we have counts for

collaborators

9 papers

cs.LG202124 cited

Learning where to learn: Gradient sparsity in meta and continual learning

Johannes von Oswald, Dominic Zhao, Seijin Kobayashi +4

Finding neural network weights that generalize well from small datasets is difficult. A promising approach is to learn a weight initialization such that a small number of weight ch…

cs.LG2021

Posterior Meta-Replay for Continual Learning

Christian Henning, Maria R. Cervera, Francesco D'Angelo +6

Learning a sequence of tasks without access to i.i.d. observations is a widely studied form of continual learning (CL) that remains challenging. In principle, Bayesian learning dir…

q-bio.NC2020

Conductance-based dendrites perform reliability-weighted opinion pooling

Jakob Jordan, João Sacramento, Mihai A. Petrovici +1

Cue integration, the combination of different sources of information to reduce uncertainty, is a fundamental computational principle of brain function. Starting from a normative mo…

cs.LG2020

A Theoretical Framework for Target Propagation

Alexander Meulemans, Francesco S. Carzaniga, Johan A. K. Suykens +2

The success of deep learning, a brain-inspired form of AI, has sparked interest in understanding how the brain could similarly learn across multiple layers of neurons. However, the…

q-bio.NC20192 cited

Ghost Units Yield Biologically Plausible Backprop in Deep Neural Networks

Thomas Mesnard, Gaetan Vignoud, Joao Sacramento +2

In the past few years, deep learning has transformed artificial intelligence research and led to impressive performance in various difficult tasks. However, it is still unclear how…

q-bio.NC2018

Dendritic cortical microcircuits approximate the backpropagation algorithm

João Sacramento, Rui Ponte Costa, Yoshua Bengio +1

Deep learning has seen remarkable developments over the last years, many of them inspired by neuroscience. However, the main learning mechanism behind these advances - error backpr…