{"editor":[{"first_name":"Igor","last_name":"Farkaš","full_name":"Farkaš, Igor"},{"full_name":"Masulli, Paolo","last_name":"Masulli","first_name":"Paolo"},{"last_name":"Wermter","full_name":"Wermter, Stefan","first_name":"Stefan"}],"publisher":"Springer International Publishing","extern":"1","author":[{"last_name":"Ostrau","orcid_put_code_url":"https://api.orcid.org/v2.0/0000-0003-1551-3848/work/162309048","full_name":"Ostrau, Christoph","id":"250133","first_name":"Christoph","orcid":"0000-0003-1551-3848"},{"first_name":"Jonas","last_name":"Homburg","full_name":"Homburg, Jonas"},{"first_name":"Christian","last_name":"Klarhorst","full_name":"Klarhorst, Christian"},{"full_name":"Thies, Michael","last_name":"Thies","first_name":"Michael"},{"first_name":"Ulrich","last_name":"Rückert","full_name":"Rückert, Ulrich"}],"doi":"10.1007/978-3-030-61616-8_49","quality_controlled":"1","type":"conference","publication_identifier":{"eissn":["1611-3349"],"eisbn":["978-3-030-61616-8"],"isbn":["978-3-030-61615-1"],"issn":["0302-9743"]},"conference":{"name":"29th International Conference on Artificial Neural Networks","location":"Bratislava, Slovakia","start_date":"2020-09-15","end_date":"2020-09-18"},"abstract":[{"text":"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.","lang":"eng"}],"series_title":"Lecture Notes in Computer Science","place":"Cham","date_updated":"2024-06-25T11:56:56Z","alternative_id":["2641"],"page":"610-621","language":[{"iso":"eng"}],"publication_status":"published","year":"2020","publication":"Artificial Neural Networks and Machine Learning – ICANN 2020. 29th International Conference on Artificial Neural Networks, Bratislava, Slovakia, September 15–18, 2020, Proceedings, Part II","date_created":"2023-03-24T10:24:42Z","title":"Benchmarking Deep Spiking Neural Networks on Neuromorphic Hardware","citation":{"ama":"Ostrau C, Homburg J, Klarhorst C, Thies M, Rückert U. Benchmarking Deep Spiking Neural Networks on Neuromorphic Hardware. In: Farkaš I, Masulli P, Wermter S, eds. <i>Artificial Neural Networks and Machine Learning – ICANN 2020. 29th International Conference on Artificial Neural Networks, Bratislava, Slovakia, September 15–18, 2020, Proceedings, Part II</i>. Lecture Notes in Computer Science. Cham: Springer International Publishing; 2020:610-621. doi:<a href=\"https://doi.org/10.1007/978-3-030-61616-8_49\">10.1007/978-3-030-61616-8_49</a>","mla":"Ostrau, Christoph, et al. “Benchmarking Deep Spiking Neural Networks on Neuromorphic Hardware.” <i>Artificial Neural Networks and Machine Learning – ICANN 2020. 29th International Conference on Artificial Neural Networks, Bratislava, Slovakia, September 15–18, 2020, Proceedings, Part II</i>, edited by Igor Farkaš et al., Springer International Publishing, 2020, pp. 610–21, doi:<a href=\"https://doi.org/10.1007/978-3-030-61616-8_49\">10.1007/978-3-030-61616-8_49</a>.","bibtex":"@inproceedings{Ostrau_Homburg_Klarhorst_Thies_Rückert_2020, place={Cham}, series={Lecture Notes in Computer Science}, title={Benchmarking Deep Spiking Neural Networks on Neuromorphic Hardware}, DOI={<a href=\"https://doi.org/10.1007/978-3-030-61616-8_49\">10.1007/978-3-030-61616-8_49</a>}, booktitle={Artificial Neural Networks and Machine Learning – ICANN 2020. 29th International Conference on Artificial Neural Networks, Bratislava, Slovakia, September 15–18, 2020, Proceedings, Part II}, publisher={Springer International Publishing}, author={Ostrau, Christoph and Homburg, Jonas and Klarhorst, Christian and Thies, Michael and Rückert, Ulrich}, editor={Farkaš, Igor and Masulli, Paolo and Wermter, StefanEditors}, year={2020}, pages={610–621}, collection={Lecture Notes in Computer Science} }","apa":"Ostrau, C., Homburg, J., Klarhorst, C., Thies, M., &#38; Rückert, U. (2020). Benchmarking Deep Spiking Neural Networks on Neuromorphic Hardware. In I. Farkaš, P. Masulli, &#38; S. Wermter (Eds.), <i>Artificial Neural Networks and Machine Learning – ICANN 2020. 29th International Conference on Artificial Neural Networks, Bratislava, Slovakia, September 15–18, 2020, Proceedings, Part II</i> (pp. 610–621). Cham: Springer International Publishing. <a href=\"https://doi.org/10.1007/978-3-030-61616-8_49\">https://doi.org/10.1007/978-3-030-61616-8_49</a>","chicago":"Ostrau, Christoph, Jonas Homburg, Christian Klarhorst, Michael Thies, and Ulrich Rückert. “Benchmarking Deep Spiking Neural Networks on Neuromorphic Hardware.” In <i>Artificial Neural Networks and Machine Learning – ICANN 2020. 29th International Conference on Artificial Neural Networks, Bratislava, Slovakia, September 15–18, 2020, Proceedings, Part II</i>, edited by Igor Farkaš, Paolo Masulli, and Stefan Wermter, 610–21. Lecture Notes in Computer Science. Cham: Springer International Publishing, 2020. <a href=\"https://doi.org/10.1007/978-3-030-61616-8_49\">https://doi.org/10.1007/978-3-030-61616-8_49</a>.","ieee":"C. Ostrau, J. Homburg, C. Klarhorst, M. Thies, and U. Rückert, “Benchmarking Deep Spiking Neural Networks on Neuromorphic Hardware,” in <i>Artificial Neural Networks and Machine Learning – ICANN 2020. 29th International Conference on Artificial Neural Networks, Bratislava, Slovakia, September 15–18, 2020, Proceedings, Part II</i>, Bratislava, Slovakia, 2020, pp. 610–621.","alphadin":"<span style=\"font-variant:small-caps;\">Ostrau, Christoph</span> ; <span style=\"font-variant:small-caps;\">Homburg, Jonas</span> ; <span style=\"font-variant:small-caps;\">Klarhorst, Christian</span> ; <span style=\"font-variant:small-caps;\">Thies, Michael</span> ; <span style=\"font-variant:small-caps;\">Rückert, Ulrich</span>: Benchmarking Deep Spiking Neural Networks on Neuromorphic Hardware. In: <span style=\"font-variant:small-caps;\">Farkaš, I.</span> ; <span style=\"font-variant:small-caps;\">Masulli, P.</span> ; <span style=\"font-variant:small-caps;\">Wermter, S.</span> (Hrsg.): <i>Artificial Neural Networks and Machine Learning – ICANN 2020. 29th International Conference on Artificial Neural Networks, Bratislava, Slovakia, September 15–18, 2020, Proceedings, Part II</i>, <i>Lecture Notes in Computer Science</i>. Cham : Springer International Publishing, 2020, S. 610–621","short":"C. Ostrau, J. Homburg, C. Klarhorst, M. Thies, U. Rückert, in: I. Farkaš, P. Masulli, S. Wermter (Eds.), Artificial Neural Networks and Machine Learning – ICANN 2020. 29th International Conference on Artificial Neural Networks, Bratislava, Slovakia, September 15–18, 2020, Proceedings, Part II, Springer International Publishing, Cham, 2020, pp. 610–621."},"user_id":"220548","_id":"2668","status":"public"}