5 citations · 14 across the 5 of their papers we have counts for
6 papers
Beyond Pairwise Correlations: Higher-Order Redundancies in Self-Supervised Representation Learning
David Zollikofer, Béni Egressy, Frederik Benzing +2
Several self-supervised learning (SSL) approaches have shown that redundancy reduction in the feature embedding space is an effective tool for representation learning. However, the…
Random initialisations performing above chance and how to find them
Frederik Benzing, Simon Schug, Robert Meier +5
Neural networks trained with stochastic gradient descent (SGD) starting from different random initialisations typically find functionally very similar solutions, raising the questi…
Gradient Descent on Neurons and its Link to Approximate Second-Order Optimization
Frederik Benzing
Second-order optimizers are thought to hold the potential to speed up neural network training, but due to the enormous size of the curvature matrix, they typically require approxim…
Unifying Regularisation Methods for Continual Learning
Frederik Benzing
Continual Learning addresses the challenge of learning a number of different tasks sequentially. The goal of maintaining knowledge of earlier tasks without re-accessing them starkl…
Optimal Kronecker-Sum Approximation of Real Time Recurrent Learning
Frederik Benzing, Marcelo Matheus Gauy, Asier Mujika +2
One of the central goals of Recurrent Neural Networks (RNNs) is to learn long-term dependencies in sequential data. Nevertheless, the most popular training method, Truncated Backpr…
Long directed rainbow cycles and rainbow spanning trees
Frederik Benzing, Alexey Pokrovskiy, Benny Sudakov
A subgraph of an edge-coloured graph is called rainbow if all its edges have different colours. The problem of finding rainbow subgraphs goes back to the work of Euler on transvers…