31 citations · 39 across the 3 of their papers we have counts for
4 papers
Mechanistic Interpretability for AI Safety -- A Review
Leonard Bereska, Efstratios Gavves
Understanding AI systems' inner workings is critical for ensuring value alignment and safety. This review explores mechanistic interpretability: reverse engineering the computation…
Tractable Dendritic RNNs for Reconstructing Nonlinear Dynamical Systems
Manuel Brenner, Florian Hess, Jonas M. Mikhaeil +4
In many scientific disciplines, we are interested in inferring the nonlinear dynamical system underlying a set of observed time series, a challenging task in the face of chaotic be…
Continual Learning of Dynamical Systems with Competitive Federated Reservoir Computing
Leonard Bereska, Efstratios Gavves
Machine learning recently proved efficient in learning differential equations and dynamical systems from data. However, the data is commonly assumed to originate from a single neve…
Unsupervised Part-Based Disentangling of Object Shape and Appearance
Dominik Lorenz, Leonard Bereska, Timo Milbich +1
Large intra-class variation is the result of changes in multiple object characteristics. Images, however, only show the superposition of different variable factors such as appearan…