Nicolas Zucchet

Publication Activity (10 Years)

Years Active: 2021-2024
Publications (10 Years): 14

Top Topics

Backpropagation Algorithm

Recurrent Neural Networks

Levenberg Marquardt

Top Venues

Publications

Nicolas Zucchet, Antonio Orvieto
Recurrent neural networks: vanishing and exploding gradients are not the end of the story. CoRR (2024)
Nicolas Zucchet, Robert Meier, Simon Schug, Asier Mujika, João Sacramento
Online learning of long-range dependencies. NeurIPS (2023)
Nicolas Zucchet, Seijin Kobayashi, Yassir Akram, Johannes von Oswald, Maxime Larcher, Angelika Steger, João Sacramento
Gated recurrent neural networks discover attention. CoRR (2023)
Johannes von Oswald, Eyvind Niklasson, Maximilian Schlegel, Seijin Kobayashi, Nicolas Zucchet, Nino Scherrer, Nolan Miller, Mark Sandler, Blaise Agüera y Arcas, Max Vladymyrov, Razvan Pascanu, João Sacramento
Uncovering mesa-optimization algorithms in Transformers. CoRR (2023)
Nicolas Zucchet, Robert Meier, Simon Schug, Asier Mujika, João Sacramento
Online learning of long-range dependencies. CoRR (2023)
Alexander Meulemans, Nicolas Zucchet, Seijin Kobayashi, Johannes von Oswald, João Sacramento
The least-control principle for local learning at equilibrium. NeurIPS (2022)
Alexander Meulemans, Nicolas Zucchet, Seijin Kobayashi, Johannes von Oswald, João Sacramento
The least-control principle for learning at equilibrium. CoRR (2022)
Nicolas Zucchet, João Sacramento
Beyond backpropagation: implicit gradients for bilevel optimization. CoRR (2022)
Frederik Benzing, Simon Schug, Robert Meier, Johannes von Oswald, Yassir Akram, Nicolas Zucchet, Laurence Aitchison, Angelika Steger
Random initialisations performing above chance and how to find them. CoRR (2022)
Nicolas Zucchet, Simon Schug, Johannes von Oswald, Dominic Zhao, João Sacramento
A contrastive rule for meta-learning. NeurIPS (2022)
Nicolas Zucchet, João Sacramento
Beyond Backpropagation: Bilevel Optimization Through Implicit Differentiation and Equilibrium Propagation. Neural Comput. 34 (12) (2022)
Johannes von Oswald, Dominic Zhao, Seijin Kobayashi, Simon Schug, Massimo Caccia, Nicolas Zucchet, João Sacramento
Learning where to learn: Gradient sparsity in meta and continual learning. NeurIPS (2021)
Nicolas Zucchet, Simon Schug, Johannes von Oswald, Dominic Zhao, João Sacramento
A contrastive rule for meta-learning. CoRR (2021)
Johannes von Oswald, Dominic Zhao, Seijin Kobayashi, Simon Schug, Massimo Caccia, Nicolas Zucchet, João Sacramento
Learning where to learn: Gradient sparsity in meta and continual learning. CoRR (2021)