Zobrazeno 1 - 10
of 1 688
pro vyhledávání: '"Schemmel, A"'
Autor:
Arnold, Elias, Edelmann, Eike-Manuel, von Bank, Alexander, Müller, Eric, Schmalen, Laurent, Schemmel, Johannes
Spiking neural networks (SNNs) emulated on dedicated neuromorphic accelerators promise to offer energy-efficient signal processing. However, the neuromorphic advantage over traditional algorithms still remains to be demonstrated in real-world applica
Externí odkaz:
http://arxiv.org/abs/2412.03129
The study of plasticity in spiking neural networks is an active area of research. However, simulations that involve complex plasticity rules, dense connectivity/high synapse counts, complex neuron morphologies, or extended simulation times can be com
Externí odkaz:
http://arxiv.org/abs/2412.03128
Autor:
Schmidt, Hartmut, Grübl, Andreas, Montes, José, Müller, Eric, Schmitt, Sebastian, Schemmel, Johannes
As numerical simulations grow in size and complexity, they become increasingly resource-intensive in terms of time and energy. While specialized hardware accelerators often provide order-of-magnitude gains and are state of the art in other scientific
Externí odkaz:
http://arxiv.org/abs/2412.02619
Autor:
Atoui, Amani, Kaiser, Jakob, Billaudelle, Sebastian, Spilger, Philipp, Müller, Eric, Luboeinski, Jannik, Tetzlaff, Christian, Schemmel, Johannes
As numerical simulations grow in complexity, their demands on computing time and energy increase. Hardware accelerators offer significant efficiency gains in many computationally intensive scientific fields, but their use in computational neuroscienc
Externí odkaz:
http://arxiv.org/abs/2412.02515
The development of mechanistic models of physical systems is essential for understanding their behavior and formulating predictions that can be validated experimentally. Calibration of these models, especially for complex systems, requires automated
Externí odkaz:
http://arxiv.org/abs/2412.02437
Autor:
Göltz, Julian, Weber, Jimmy, Kriener, Laura, Billaudelle, Sebastian, Lake, Peter, Schemmel, Johannes, Payvand, Melika, Petrovici, Mihai A.
Spiking neural networks (SNNs) inherently rely on the timing of signals for representing and processing information. Incorporating trainable transmission delays, alongside synaptic weights, is crucial for shaping these temporal dynamics. While recent
Externí odkaz:
http://arxiv.org/abs/2404.19165
Autor:
Stradmann, Yannik, Göltz, Julian, Petrovici, Mihai A., Schemmel, Johannes, Billaudelle, Sebastian
With an increasing presence of science throughout all parts of society, there is a rising expectation for researchers to effectively communicate their work and, equally, for teachers to discuss contemporary findings in their classrooms. While the com
Externí odkaz:
http://arxiv.org/abs/2404.16664
Autor:
Müller, Eric, Althaus, Moritz, Arnold, Elias, Spilger, Philipp, Pehle, Christian, Schemmel, Johannes
Traditional neuromorphic hardware architectures rely on event-driven computation, where the asynchronous transmission of events, such as spikes, triggers local computations within synapses and neurons. While machine learning frameworks are commonly u
Externí odkaz:
http://arxiv.org/abs/2401.16841
Autor:
Arnold, Elias, Spilger, Philipp, Straub, Jan V., Müller, Eric, Dold, Dominik, Meoni, Gabriele, Schemmel, Johannes
We present a novel software feature for the BrainScaleS-2 accelerated neuromorphic platform that facilitates the partitioned emulation of large-scale spiking neural networks. This approach is well suited for deep spiking neural networks and allows fo
Externí odkaz:
http://arxiv.org/abs/2401.16840
Autor:
Schreiber, Korbinian, Wunderlich, Timo, Spilger, Philipp, Billaudelle, Sebastian, Cramer, Benjamin, Stradmann, Yannik, Pehle, Christian, Müller, Eric, Petrovici, Mihai A., Schemmel, Johannes, Meier, Karlheinz
Bees display the remarkable ability to return home in a straight line after meandering excursions to their environment. Neurobiological imaging studies have revealed that this capability emerges from a path integration mechanism implemented within th
Externí odkaz:
http://arxiv.org/abs/2401.00473