Zobrazeno 1 - 10
of 26
pro vyhledávání: '"David Rotermund"'
Publikováno v:
IEEE Access, Vol 9, Pp 80603-80620 (2021)
Spiking neural networks (SNNs) represent a promising alternative to conventional neural networks. In particular, the so-called Spike-by-Spike (SbS) neural networks provide exceptional noise robustness and reduced complexity. However, deep SbS network
Externí odkaz:
https://doaj.org/article/f0b7e98afae54a70adb46686eaa52e19
Publikováno v:
HardwareX, Vol 6, Iss , Pp - (2019)
Recent progress in neuro-prosthetic technology gives rise to the hope that in the future blind people might regain some degree of visual perception. It was shown that electrically stimulating the brain can be used to produce simple visual impressions
Externí odkaz:
https://doaj.org/article/9ad947a448f7491388244471c603521a
Autor:
David Rotermund, Klaus R. Pawelzik
Publikováno v:
Frontiers in Computational Neuroscience, Vol 13 (2019)
Artificial neural networks (ANNs) are important building blocks in technical applications. They rely on noiseless continuous signals in stark contrast to the discrete action potentials stochastically exchanged among the neurons in real brains. We pro
Externí odkaz:
https://doaj.org/article/28f988716e044db79cd227cf833b792c
Autor:
David Rotermund, Jonas Pistor, Janpeter Hoeffmann, Tim Schellenberg, Dmitriy Boll, Elena Tolstosheeva, Dieter Gauck, Heiko Stemmann, Dagmar Peters-Drolshagen, Andreas Kurt Kreiter, Martin Schneider, Steffen Paul, Walter Lang, Klaus Richard Pawelzik
Publikováno v:
Sensors, Vol 17, Iss 4, p 761 (2017)
Implantable neuronal interfaces to the brain are an important keystone for future medical applications. However, entering this field of research is difficult since such an implant requires components from many different areas of technology. Since the
Externí odkaz:
https://doaj.org/article/58b58c9bb3b945eeb72fa82e4280f945
Networks of spiking neurons promise to combine energy efficiency with high performance. However, spiking models that match the performance of current state-of-the-art networks while requiring moderate computational resources are still lacking. Here w
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::5246f3bc82f58ac29d71719117b7bdb4
https://doi.org/10.1101/2023.04.22.537923
https://doi.org/10.1101/2023.04.22.537923
Publikováno v:
IEEE Access, Vol 9, Pp 80603-80620 (2021)
Spiking neural networks (SNNs) represent a promising alternative to conventional neural networks. In particular, the so-called Spike-by-Spike (SbS) neural networks provide exceptional noise robustness and reduced complexity. However, deep SbS network
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::cbf6274b311126088a665743c36b6499
https://ieeexplore.ieee.org/document/9444398/
https://ieeexplore.ieee.org/document/9444398/
Publikováno v:
MOCAST
Although artificial Spiking Neural Networks provide numerous advantages versus the traditional non spiking ones, their high complexity is limiting the use to server computers or dedicated ASIC implementations. As an alternative, the recently proposed
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::cdefd5b14a778e4ef97f921f19ace5e8
https://doi.org/10.1109/mocast49295.2020.9200288
https://doi.org/10.1109/mocast49295.2020.9200288
Autor:
Klaus Pawelzik, David Rotermund
Artificial deep convolutional networks (DCNs) meanwhile beat even human performance in challenging tasks. Recently DCNs were shown to also predict real neuronal responses. Their relevance for understanding the neuronal networks in the brain, however,
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::6c33b4d94be326e054f5e0c5d6ade3b1
Autor:
David Rotermund, Klaus Pawelzik
1 Abstract The increase in computational power by faster computers as well as application specific integrated circuits (ASICs) lead to re-consideration of neuronal networks for pattern recognition and other applications in artificial intelligence (AI
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::dd1e96c917bf5742747ea052b146b949
Publikováno v:
HardwareX, Vol 6, Iss, Pp-(2019)
Recent progress in neuro-prosthetic technology gives rise to the hope that in the future blind people might regain some degree of visual perception. It was shown that electrically stimulating the brain can be used to produce simple visual impressions
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::71dc125cca5afbc578fc89aea23f9a2a
https://doi.org/10.1101/141184
https://doi.org/10.1101/141184