no code implementations • 11 Oct 2019 • Florian Meier, Asier Mujika, Marcelo Matheus Gauy, Angelika Steger
Finally, we evaluate our approach empirically on MNIST and reinforcement learning tasks and show that it considerably improves the gradient estimation of ES at no extra computational cost.
no code implementations • 16 Aug 2018 • Hafsteinn Einarsson, Marcelo Matheus Gauy, Johannes Lengler, Florian Meier, Asier Mujika, Angelika Steger, Felix Weissenberger
For the first setup, we give a schedule that achieves a runtime of $(1\pm o(1))\beta n \ln n$, where $\beta \approx 3. 552$, which is an asymptotic improvement over the runtime of the static setup.
no code implementations • NeurIPS 2018 • Asier Mujika, Florian Meier, Angelika Steger
Despite all the impressive advances of recurrent neural networks, sequential data is still in need of better modelling.
1 code implementation • NeurIPS 2017 • Asier Mujika, Florian Meier, Angelika Steger
Processing sequential data of variable length is a major challenge in a wide range of applications, such as speech recognition, language modeling, generative image modeling and machine translation.
Ranked #10 on Language Modelling on Penn Treebank (Character Level)
1 code implementation • 29 Jan 2015 • Florian Meier, Volker Turau
The unslotted CSMA/CA MAC layer of IEEE 802. 15. 4 is closely modeled as well as an enhanced model of the neighborhood allows for consideration of collisions of packets including interferences with acknowledgements.
Networking and Internet Architecture