15 citations · 77 across the 20 of their papers we have counts for
6 papers · 1 filter
Efficient LSTM Training with Eligibility Traces
Michael Hoyer, Shahram Eivazi, Sebastian Otte
Training recurrent neural networks is predominantly achieved via backpropagation through time (BPTT). However, this algorithm is not an optimal solution from both a biological and…
Generating Sparse Counterfactual Explanations For Multivariate Time Series
Jana Lang, Martin Giese, Winfried Ilg +1
Since neural networks play an increasingly important role in critical sectors, explaining network predictions has become a key research topic. Counterfactual explanations can help…
A Taxonomy of Recurrent Learning Rules
Guillermo Martín-Sánchez, Sander Bohté, Sebastian Otte
Backpropagation through time (BPTT) is the de facto standard for training recurrent neural networks (RNNs), but it is non-causal and non-local. Real-time recurrent learning is a ca…
Binding Dancers Into Attractors
Franziska Kaltenberger, Sebastian Otte, Martin V. Butz
To effectively perceive and process observations in our environment, feature binding and perspective taking are crucial cognitive abilities. Feature binding combines observed featu…
Learning What and Where: Disentangling Location and Identity Tracking Without Supervision
Manuel Traub, Sebastian Otte, Tobias Menge +3
Our brain can almost effortlessly decompose visual data streams into background and salient objects. Moreover, it can anticipate object motion and interactions, which are crucial a…
Inference of Affordances and Active Motor Control in Simulated Agents
Fedor Scholz, Christian Gumbsch, Sebastian Otte +1
Flexible, goal-directed behavior is a fundamental aspect of human life. Based on the free energy minimization principle, the theory of active inference formalizes the generation of…