Picture for João Sacramento

João Sacramento

Online learning of long-range dependencies

May 25, 2023
Nicolas Zucchet, Robert Meier, Simon Schug, Asier Mujika, João Sacramento

Access Paper or Ask Questions

The least-control principle for learning at equilibrium

Jul 04, 2022
Alexander Meulemans, Nicolas Zucchet, Seijin Kobayashi, Johannes von Oswald, João Sacramento

Figure 1 for The least-control principle for learning at equilibrium

Figure 2 for The least-control principle for learning at equilibrium

Figure 3 for The least-control principle for learning at equilibrium

Figure 4 for The least-control principle for learning at equilibrium

* 52 pages, 3 figures

Access Paper or Ask Questions

Beyond backpropagation: implicit gradients for bilevel optimization

May 06, 2022
Nicolas Zucchet, João Sacramento

Figure 1 for Beyond backpropagation: implicit gradients for bilevel optimization

Figure 2 for Beyond backpropagation: implicit gradients for bilevel optimization

Figure 3 for Beyond backpropagation: implicit gradients for bilevel optimization

Access Paper or Ask Questions

Minimizing Control for Credit Assignment with Strong Feedback

Apr 14, 2022
Alexander Meulemans, Matilde Tristany Farinha, Maria R. Cervera, João Sacramento, Benjamin F. Grewe

Figure 1 for Minimizing Control for Credit Assignment with Strong Feedback

Figure 2 for Minimizing Control for Credit Assignment with Strong Feedback

Figure 3 for Minimizing Control for Credit Assignment with Strong Feedback

Figure 4 for Minimizing Control for Credit Assignment with Strong Feedback

* 25 pages, 3 figures

Access Paper or Ask Questions

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

Oct 27, 2021
Johannes von Oswald, Dominic Zhao, Seijin Kobayashi, Simon Schug, Massimo Caccia, Nicolas Zucchet, João Sacramento

Figure 1 for Learning where to learn: Gradient sparsity in meta and continual learning

Figure 2 for Learning where to learn: Gradient sparsity in meta and continual learning

Figure 3 for Learning where to learn: Gradient sparsity in meta and continual learning

Figure 4 for Learning where to learn: Gradient sparsity in meta and continual learning

* Published at NeurIPS 2021

Access Paper or Ask Questions

Credit Assignment in Neural Networks through Deep Feedback Control

Jun 15, 2021
Alexander Meulemans, Matilde Tristany Farinha, Javier García Ordóñez, Pau Vilimelis Aceituno, João Sacramento, Benjamin F. Grewe

Figure 1 for Credit Assignment in Neural Networks through Deep Feedback Control

Figure 2 for Credit Assignment in Neural Networks through Deep Feedback Control

Figure 3 for Credit Assignment in Neural Networks through Deep Feedback Control

Figure 4 for Credit Assignment in Neural Networks through Deep Feedback Control

* 14 pages and 3 figures in the main manuscript; 45 pages and 14 figures in the supplementary materials

Access Paper or Ask Questions

A contrastive rule for meta-learning

Apr 19, 2021
Nicolas Zucchet, Simon Schug, Johannes von Oswald, Dominic Zhao, João Sacramento

Figure 1 for A contrastive rule for meta-learning

Figure 2 for A contrastive rule for meta-learning

Figure 3 for A contrastive rule for meta-learning

Figure 4 for A contrastive rule for meta-learning

* 29 pages, 9 figures

Access Paper or Ask Questions