no code implementations • 29 Sep 2021 • Martin Hofmann, Moritz F. P. Becker, Christian Tetzlaff, Patrick Mäder
Various advancements in artificial neural networks (ANNs) are inspired by biological concepts, e. g., the artificial neuron, an efficient model of biological nerve cells demonstrating learning capabilities on large amounts of data.
no code implementations • 25 Sep 2021 • Carlo Michaelis, Andrew B. Lehr, Winfried Oed, Christian Tetzlaff
Developing intelligent neuromorphic solutions remains a challenging endeavour.
no code implementations • NeurIPS Workshop ICBINB 2021 • David Kappel, Franscesco Negri, Christian Tetzlaff
This general formulation allows us to use the model also for online learning where no knowledge about task switching times is given to the network.
no code implementations • 23 Mar 2021 • David Kappel, Christian Tetzlaff
The free energy principle (FEP) is a mathematical framework that describes how biological systems self-organize and survive in their environment.
1 code implementation • 26 Aug 2020 • Carlo Michaelis, Andrew B. Lehr, Christian Tetzlaff
With this, we show that the anisotropic network on Loihi reliably encodes sequential patterns of neural activity, each representing a robotic action, and that the patterns allow the generation of multidimensional trajectories on control-relevant timescales.
no code implementations • 13 Jun 2017 • Sebastian Herzog, Christian Tetzlaff, Florentin Wörgötter
The structure of the majority of modern deep neural networks is characterized by uni- directional feed-forward connectivity across a very large number of layers.