no code implementations • 28 Jul 2022 • Fabian C. Weigend, Edward Gray, Oliver Obst, Jason Siegler
In this work, we hypothesised that the benefits of the model come at the cost of inaccurate predictions of metabolic responses to exercise such as $\dot{V}_{\mathrm{O}_2}$.
no code implementations • 19 May 2022 • Norbert Michael Mayer, Oliver Obst
This connection between fractal dimension and network connectivity is an interesting new direction for recurrent neural network initialization and reservoir computing.
1 code implementation • 12 Jul 2021 • Rajvir Kaur, Jeewani Anupama Ginige, Oliver Obst
Efforts are still required to improve ICD code prediction accuracy, availability of large-scale de-identified clinical corpora with the latest version of the classification system.
1 code implementation • 16 Apr 2021 • Fabian Clemens Weigend, Jason Siegler, Oliver Obst
This work proposes to use evolutionary computation as a pathway to allow a new perspective on the modeling of energy expenditure and recovery of an individual athlete during exercise.
no code implementations • 4 Apr 2018 • Trevor Barron, Oliver Obst, Heni Ben Amor
A key insight of our approach is that this dynamics model can be learned in the latent feature space of a value function, representing the dynamics of the agent and the environment.
2 code implementations • 9 Feb 2018 • Frieder Stolzenburg, Sandra Litz, Olivia Michael, Oliver Obst
Recurrent neural networks are a powerful means to cope with time series.
1 code implementation • 6 Nov 2017 • Olivia Michael, Oliver Obst, Falk Schmidsberger, Frieder Stolzenburg
These data are made available as CSV files, as well as in the original soccer simulator formats.
no code implementations • 19 Aug 2017 • Olivia Michael, Oliver Obst, Falk Schmidsberger, Frieder Stolzenburg
With the proposed approach, we can segment games into sequences of situations that are learnt in an unsupervised way, and learn conceptors that are useful for the prediction of the near future of the respective situation.
no code implementations • 12 Mar 2017 • Olivia Michael, Oliver Obst
RoboCup offers a set of benchmark problems for Artificial Intelligence in form of official world championships since 1997.
no code implementations • 17 Mar 2014 • David Budden, Peter Wang, Oliver Obst, Mikhail Prokopenko
A proposed new competition format is found to reduce variation from the resultant statistically significant team performance rankings by 75% and 67%, when compared to the actual competition results from RoboCup 2012 and 2013 respectively.
no code implementations • 6 Sep 2013 • Oliver Obst, Adrian Trinchi, Simon G. Hardin, Matthew Chadwick, Ivan Cole, Tim H. Muster, Nigel Hoschke, Diet Ostry, Don Price, Khoa N. Pham, Tim Wark
This work describes preliminary steps towards nano-scale reservoir computing using quantum dots.
no code implementations • 6 Sep 2013 • Oliver Obst, Joschka Boedecker
We review attempts that have been made towards understanding the computational properties and mechanisms of input-driven dynamical systems like RNNs, and reservoir computing networks in particular.