1 citations · 1 across the 2 of their papers we have counts for
7 papers
Bio-Inspired, Task-Free Continual Learning through Activity Regularization
Francesco Lässig, Pau Vilimelis Aceituno, Martino Sorbaro +1
The ability to sequentially learn multiple tasks without forgetting is a key skill of biological brains, whereas it represents a major challenge to the field of deep learning. To a…
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…
Minimizing costs of communication with random constant weight codes
Pau Vilimelis Aceituno
We present a framework for minimizing costs in constant weight codes while maintaining a certain amount of differentiable codewords. Our calculations are based on a combinatorial v…
Resonances induced by Spiking Time Dependent Plasticity
Pau Vilimelis Aceituno
Neural populations exposed to a certain stimulus learn to represent it better. However, the process that leads local, self-organized rules to do so is unclear. We address the quest…
Synaptic Time-Dependent Plasticity Leads to Efficient Coding of Predictions
Pau Vilimelis Aceituno, Masud Ehsani, Jürgen Jost
Latency reduction of postsynaptic spikes is a well-known effect of Synaptic Time-Dependent Plasticity. We expand this notion for long postsynaptic spike trains, showing that, for a…
Universal hypotrochoidic law for random matrices with cyclic correlations
Pau Vilimelis Aceituno, Tim Rogers, Henning Schomerus
The celebrated elliptic law describes the distribution of eigenvalues of random matrices with correlations between off-diagonal pairs of elements, having applications to a wide ran…