no code implementations • 7 Mar 2024 • Halil Yigit Oksuz, Fabio Molinari, Henning Sprekeler, Joerg Raisch
Over-the-Air Computation is a beyond-5G communication strategy that has recently been shown to be useful for the decentralized training of machine learning models due to its efficiency.
1 code implementation • 31 May 2023 • Robert Tjarko Lange, Henning Sprekeler
Is the lottery ticket phenomenon an idiosyncrasy of gradient-based training or does it generalize to evolutionary optimization?
no code implementations • 8 May 2023 • Halil Yigit Oksuz, Fabio Molinari, Henning Sprekeler, Jörg Raisch
This strategy, often called federated learning, is mainly employed for two reasons: (i) improving resource-efficiency by avoiding to share potentially large datasets and (ii) guaranteeing privacy of local agents' data.
no code implementations • ICLR 2022 • Marc Aurel Vischer, Robert Tjarko Lange, Henning Sprekeler
But how is the performance of winning lottery tickets affected by the distributional shift inherent to reinforcement learning problems?
no code implementations • 9 Oct 2020 • Robert Tjarko Lange, Henning Sprekeler
Animals are equipped with a rich innate repertoire of sensory, behavioral and motor skills, which allows them to interact with the world immediately after birth.
no code implementations • NeurIPS 2009 • Henning Sprekeler, Guillaume Hennequin, Wulfram Gerstner
Here, we show that different learning rules emerge from a policy gradient approach depending on which features of the spike trains are assumed to influence the reward signals, i. e., depending on which neural code is in effect.