42 citations · 132 across the 20 of their papers we have counts for
30 papers
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…
Solving Static Permutation Mastermind using Queries
Maxime Larcher, Anders Martinsson, Angelika Steger
Permutation Mastermind is a version of the classical mastermind game in which the number of positions is equal to the number of colors , and repetition of colors is not allo…
An O(n) time algorithm for finding Hamilton cycles with high probability
Rajko Nenadov, Angelika Steger, Pascal Su
We design a randomized algorithm that finds a Hamilton cycle in time with high probability in a random graph with edge probability . T…
Improving Gradient Estimation in Evolutionary Strategies With Past Descent Directions
Florian Meier, Asier Mujika, Marcelo Matheus Gauy +1
Evolutionary Strategies (ES) are known to be an effective black-box optimization technique for deep neural networks when the true gradients cannot be computed, such as in Reinforce…
Decoupling Hierarchical Recurrent Neural Networks With Locally Computable Losses
Asier Mujika, Felix Weissenberger, Angelika Steger
Learning long-term dependencies is a key long-standing challenge of recurrent neural networks (RNNs). Hierarchical recurrent neural networks (HRNNs) have been considered a promisin…
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…