Benchmarking Deep Spiking Neural Networks on Neuromorphic Hardware

Ostrau C, Homburg JD, Klarhorst C, Thies M, Rückert U (2020)
In: Artificial Neural Networks and Machine Learning – ICANN 2020. Springer International Publishing.

Konferenzbeitrag | Veröffentlicht | Englisch
 
Download
Restricted main.pdf 505.06 KB Request a Copy
Abstract / Bemerkung
With more and more event-based neuromorphic hardware systems being developed at universities and in industry, there is a growing need for assessing their performance with domain specific measures. In this work, we use the methodology of converting pre-trained non-spiking to spiking neural networks to evaluate the performance loss and measure the energy-per-inference for three neuromorphic hardware systems (BrainScaleS, Spikey, SpiNNaker) and common simulation frameworks for CPU (NEST) and CPU/GPU (GeNN). For analog hardware we further apply a re-training technique known as hardware-in-the-loop training to cope with device mismatch. This analysis is performed for five different networks, including three networks that have been found by an automated optimization with a neural architecture search framework. We demonstrate that the conversion loss is usually below one percent for digital implementations, and moderately higher for analog systems with the benefit of much lower energy-per-inference costs.
Erscheinungsjahr
2020
Titel des Konferenzbandes
Artificial Neural Networks and Machine Learning – ICANN 2020
Konferenz
ICANN 2020
Konferenzort
Bratislava
ISBN
978-3-030-61615-1
eISBN
978-3-030-61616-8
Page URI
https://pub.uni-bielefeld.de/record/2942322

Zitieren

Ostrau C, Homburg JD, Klarhorst C, Thies M, Rückert U. Benchmarking Deep Spiking Neural Networks on Neuromorphic Hardware. In: Artificial Neural Networks and Machine Learning – ICANN 2020. Springer International Publishing; 2020.
Ostrau, C., Homburg, J. D., Klarhorst, C., Thies, M., & Rückert, U. (2020). Benchmarking Deep Spiking Neural Networks on Neuromorphic Hardware. Artificial Neural Networks and Machine Learning – ICANN 2020 Springer International Publishing. doi:10.1007/978-3-030-61616-8_49
Ostrau, C., Homburg, J. D., Klarhorst, C., Thies, M., and Rückert, U. (2020). “Benchmarking Deep Spiking Neural Networks on Neuromorphic Hardware” in Artificial Neural Networks and Machine Learning – ICANN 2020 (Springer International Publishing).
Ostrau, C., et al., 2020. Benchmarking Deep Spiking Neural Networks on Neuromorphic Hardware. In Artificial Neural Networks and Machine Learning – ICANN 2020. Springer International Publishing.
C. Ostrau, et al., “Benchmarking Deep Spiking Neural Networks on Neuromorphic Hardware”, Artificial Neural Networks and Machine Learning – ICANN 2020, Springer International Publishing, 2020.
Ostrau, C., Homburg, J.D., Klarhorst, C., Thies, M., Rückert, U.: Benchmarking Deep Spiking Neural Networks on Neuromorphic Hardware. Artificial Neural Networks and Machine Learning – ICANN 2020. Springer International Publishing (2020).
Ostrau, Christoph, Homburg, Jonas Dominik, Klarhorst, Christian, Thies, Michael, and Rückert, Ulrich. “Benchmarking Deep Spiking Neural Networks on Neuromorphic Hardware”. Artificial Neural Networks and Machine Learning – ICANN 2020. Springer International Publishing, 2020.
Volltext(e)
Name
main.pdf 505.06 KB Request a Copy
Access Level
Restricted Request a Copy
Zuletzt Hochgeladen
2020-10-26T13:29:06Z
MD5 Prüfsumme
4930cd994e757ece1f8fa64dd816f786

Export

Markieren/ Markierung löschen
Markierte Publikationen

Open Data PUB

Quellen

arXiv: 2004.01656

Suchen in

Google Scholar
ISBN Suche