22 citations · 28 across the 14 of their papers we have counts for
7 papers · 1 filter
A combination of noise and bilateral filters achieve supralinear and scalable adversarial robustness in CNNs
Nicolas Stalder, Benjamin F. Grewe, Matteo Saponati +1
The vulnerability of deep neural networks to adversarial examples poses a significant challenge for real-world deployment. Existing techniques to enhance deep network robustness re…
Continual Learning through Control Minimization
Sander de Haan, Yassine Taoudi-Benchekroun, Pau Vilimelis Aceituno +1
Catastrophic forgetting remains a fundamental challenge for neural networks when tasks are trained sequentially. In this work, we reformulate continual learning as a control proble…
Temporal horizons in forecasting: a performance-learnability trade-off
Pau Vilimelis Aceituno, Jack William Miller, Noah Marti +2
When training autoregressive models to forecast dynamical systems, a critical question arises: how far into the future should the model be trained to predict for optimal performanc…
The underlying structures of self-attention: symmetry, directionality, and emergent dynamics in Transformer training
Matteo Saponati, Pascal Sager, Pau Vilimelis Aceituno +2
Self-attention is essential to Transformer architectures, yet how information is embedded in the self-attention matrices and how different objective functions impact this process r…
Disentangling the Predictive Variance of Deep Ensembles through the Neural Tangent Kernel
Seijin Kobayashi, Pau Vilimelis Aceituno, Johannes von Oswald
Identifying unfamiliar inputs, also known as out-of-distribution (OOD) detection, is a crucial property of any decision making process. A simple and empirically validated technique…
Credit Assignment in Neural Networks through Deep Feedback Control
Alexander Meulemans, Matilde Tristany Farinha, Javier García Ordóñez +3
The success of deep learning sparked interest in whether the brain learns by using similar techniques for assigning credit to each synaptic weight for its contribution to the netwo…
Tailoring Artificial Neural Networks for Optimal Learning
Pau Vilimelis Aceituno, Yan Gang, Yang-Yu Liu
As one of the most important paradigms of recurrent neural networks, the echo state network (ESN) has been applied to a wide range of fields, from robotics to medicine, finance, an…