37 citations · 105 across the 14 of their papers we have counts for
4 papers · 1 filter
In CEM, a World Model Is Also a Proposal Mechanism
Oliver Obst, Frieder Stolzenburg
The cross-entropy method (CEM) uses world-model scores to select action sequences and fit the distribution sampled in its next iteration. A scoring error can therefore change both…
Fast Classification Learning with Neural Networks and Conceptors for Speech Recognition and Car Driving Maneuvers
Stefanie Krause, Oliver Otto, Frieder Stolzenburg
Recurrent neural networks are a powerful means in diverse applications. We show that, together with so-called conceptors, they also allow fast learning, in contrast to other deep l…
Efficient Time-Series Approximation with Linear Recurrent Neural Networks: Architecture Learning and Predictive Power
Frieder Stolzenburg, Sandra Litz, Olivia Michael +1
Recurrent neural networks are a powerful means to cope with time series. We show how autoregressive linear, i.e., linearly activated recurrent neural networks (LRNNs) can approxima…
Analysing Soccer Games with Clustering and Conceptors
Olivia Michael, Oliver Obst, Falk Schmidsberger +1
We present a new approach for identifying situations and behaviours, which we call "moves", from soccer games in the 2D simulation league. Being able to identify key situations and…