37 citations
- University of Koblenz and LandauDE4 papers
- Western Sydney UniversityAU3 papers
- California State University, Long BeachUS1 paper
- Chalmers University of TechnologySE1 paper
- Maastricht UniversityNL1 paper
- Merseburg University of Applied SciencesDE1 paper
- University of BayreuthDE1 paper
- University of GothenburgSE1 paper
- UNSW SydneyAU1 paper
Showing cs.LGShow all
3 papers · 1 filter
cs.LG2021★ 4 cited
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…
cs.LG2018★ 3 cited
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…
cs.LG2017★ 16 cited
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…