{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,25]],"date-time":"2026-02-25T17:11:50Z","timestamp":1772039510452,"version":"3.50.1"},"reference-count":81,"publisher":"MIT Press - Journals","issue":"10","content-domain":{"domain":["direct.mit.edu"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2021,9,16]]},"abstract":"<jats:title>Abstract<\/jats:title>\n               <jats:p>Up to now, modern machine learning (ML) has been based on approximating big data sets with high-dimensional functions, taking advantage of huge computational resources. We show that biologically inspired neuron models such as the leaky-integrate-and-fire (LIF) neuron provide novel and efficient ways of information processing. They can be integrated in machine learning models and are a potential target to improve ML performance. Thus, we have derived simple update rules for LIF units to numerically integrate the differential equations. We apply a surrogate gradient approach to train the LIF units via backpropagation. We demonstrate that tuning the leak term of the LIF neurons can be used to run the neurons in different operating modes, such as simple signal integrators or coincidence detectors. Furthermore, we show that the constant surrogate gradient, in combination with tuning the leak term of the LIF units, can be used to achieve the learning dynamics of more complex surrogate gradients.<\/jats:p>\n               <jats:p>To prove the validity of our method, we applied it to established image data sets (the Oxford 102 flower data set, MNIST), implemented various network architectures, used several input data encodings and demonstrated that the method is suitable to achieve state-of-the-art classification performance.<\/jats:p>\n               <jats:p>We provide our method as well as further surrogate gradient methods to train spiking neural networks via backpropagation as an open-source KERAS package to make it available to the neuroscience and machine learning community. To increase the interpretability of the underlying effects and thus make a small step toward opening the black box of machine learning, we provide interactive illustrations, with the possibility of systematically monitoring the effects of parameter changes on the learning characteristics.<\/jats:p>","DOI":"10.1162\/neco_a_01424","type":"journal-article","created":{"date-parts":[[2021,7,19]],"date-time":"2021-07-19T20:45:04Z","timestamp":1626727504000},"page":"2827-2852","update-policy":"https:\/\/doi.org\/10.1162\/mitpressjournals.corrections.policy","source":"Crossref","is-referenced-by-count":20,"title":["Integration of Leaky-Integrate-and-Fire Neurons in Standard Machine Learning Architectures to Generate Hybrid Networks: A Surrogate Gradient Approach"],"prefix":"10.1162","volume":"33","author":[{"given":"Richard C.","family":"Gerum","sequence":"first","affiliation":[{"name":"Department of Physics and Center for Vision Research, York University, Toronto, Ontario M3J 1P3 Canada gerum@yorku.ca"}]},{"given":"Achim","family":"Schilling","sequence":"additional","affiliation":[{"name":"Experimental Otolaryngology, Neuroscience Lab, University Hospital Erlangen, 91054 Erlangen, Germany; Cognitive Computational Neuroscience Group at the Chair of English Philology and Linguistics, Friedrich-Alexander University Erlangen-N\u00fcrnberg, 91054 Erlangen, Germany; and Laboratoire Neuorsciences Sensorielles et Cognitives, Aix Marseille-University, 13331 Marseille, France achim.schilling@fau."}]}],"member":"281","published-online":{"date-parts":[[2021,9,16]]},"reference":[{"key":"2021091622575080900_B1","unstructured":"Abadi, M., Agarwal, A., Barham, P., Brevdo, E., Chen, Z., Citro, C., \u2026 Zheng, X. (2015). TensorFlow: Large-scale machine learning on heterogeneous systems. Software available from tensorflow.org."},{"key":"2021091622575080900_B2","unstructured":"Atkinson, K. E.\n           (1989). An introduction to numerical analysis.New York: Wiley"},{"key":"2021091622575080900_B3","first-page":"787","volume-title":"Advances in neural information processing systems","author":"Bellec","year":"2018"},{"issue":"7","key":"2021091622575080900_B4","doi-asserted-by":"crossref","first-page":"1413","DOI":"10.1162\/089976604323057443","article-title":"Real-time computation at the edge of chaos in recurrent neural networks","volume":"16","author":"Bertschinger","year":"2004","journal-title":"Neural Computation"},{"key":"2021091622575080900_B5","doi-asserted-by":"crossref","unstructured":"Bhuiyan, M. A., Pallipuram, V. K., Smith, M. C., Taha, T., & Jalasutram, R. (2010). Acceleration of spiking neural networks in emerging multi-core and GPU architectures. In Proceedings of the IEEE International Symposium on Parallel and Distributed Processing, Workshops & PhD Forum (pp. 1\u20138). Piscataway, NJ: IEEE.","DOI":"10.1109\/IPDPSW.2010.5470899"},{"key":"2021091622575080900_B6","doi-asserted-by":"crossref","unstructured":"Bohte, S. M.\n           (2011). Error-backpropagation in networks of fractionally predictive spiking neurons. In Proceedings of the International Conference on Artificial Neural Networks (pp. 60\u201368). Berlin: Springer.","DOI":"10.1007\/978-3-642-21735-7_8"},{"key":"2021091622575080900_B7","unstructured":"Bohte, S. M., Kok, J. N., & La Poutr\u00e9, J. A. (2000). Spikeprop: Backpropagation for networks of spiking neurons. In Proceedings of the Eighth 8th European Symposium on Artificial Neural Networks (pp. 17\u201337)."},{"issue":"12","key":"2021091622575080900_B8","doi-asserted-by":"crossref","first-page":"2301","DOI":"10.1109\/TVCG.2011.185","article-title":"D3 data-driven documents","volume":"17","author":"Bostock","year":"2011","journal-title":"IEEE Transactions on Visualization and Computer Graphics"},{"key":"2021091622575080900_B9","doi-asserted-by":"crossref","DOI":"10.3389\/fnsys.2015.00151","article-title":"Philosophy of the spike: rate-based vs. spike-based theories of the brain","volume":"9","author":"Brette","year":"2015","journal-title":"Frontiers in Systems Neuroscience"},{"issue":"1","key":"2021091622575080900_B10","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1007\/s00422-006-0068-6","article-title":"A review of the integrate-and-fire neuron model: I. Homogeneous synaptic input","volume":"95","author":"Burkitt","year":"2006","journal-title":"Biological Cybernetics"},{"key":"2021091622575080900_B11","doi-asserted-by":"crossref","unstructured":"Castelvecchi, D.\n           (2016). Can we open the black box of AI?Nature News, 538(7623), 20.","DOI":"10.1038\/538020a"},{"key":"2021091622575080900_B12","unstructured":"Chollet, F.\n           (2018). Deep Learning mit Python und Keras: Das Praxis-Handbuch vom Entwickler der Keras-Bibliothek. Bonn: MITP-Verlags."},{"issue":"6364","key":"2021091622575080900_B13","doi-asserted-by":"crossref","first-page":"793","DOI":"10.1126\/science.aam9868","article-title":"A neural algorithm for a fundamental computing problem","volume":"358","author":"Dasgupta","year":"2017","journal-title":"Science"},{"key":"2021091622575080900_B14","doi-asserted-by":"crossref","unstructured":"De Laat, P. B.\n           (2018). Algorithmic decision-making based on machine learning from big data: Can transparency restore accountability?Philosophy and Technology, 31(4), 525\u2013541.","DOI":"10.1007\/s13347-017-0293-z"},{"key":"2021091622575080900_B15","doi-asserted-by":"crossref","unstructured":"Dominguez-Morales, J. P., Jimenez-Fernandez, A., Rios-Navarro, A., Cerezuela-Escudero, E., Gutierrez-Galan, D., Dominguez-Morales, M. J., & Jimenez-Moreno, G. (2016). Multilayer spiking neural network for audio samples classification using spinnaker. In Proceedings of the International Conference on Artificial Neural Networks (pp. 45\u201353). Berlin: Springer.","DOI":"10.1007\/978-3-319-44778-0_6"},{"issue":"41","key":"2021091622575080900_B16","doi-asserted-by":"crossref","first-page":"11441","DOI":"10.1073\/pnas.1604850113","article-title":"Convolutional networks for fast, energy-efficient neuromorphic computing","volume":"113","author":"Esser","year":"2016","journal-title":"Proceedings of the National Academy of Sciences"},{"key":"2021091622575080900_B17","doi-asserted-by":"crossref","unstructured":"Feng, J., Wang, Z., Zha, M., & Cao, X. (2019). Flower recognition based on transfer learning and Adam deep learning optimization algorithm. In Proceedings of the 2019 International Conference on Robotics, Intelligent Control & Artificial Intelligence (pp. 598\u2013604). New York: ACM.","DOI":"10.1145\/3366194.3366301"},{"issue":"1","key":"2021091622575080900_B18","doi-asserted-by":"crossref","first-page":"255","DOI":"10.1152\/jn.00683.2018","article-title":"Temporal resolution of single-photon responses in primate rod photoreceptors and limits imposed by cellular noise","volume":"121","author":"Field","year":"2019","journal-title":"Journal of Neurophysiology"},{"key":"2021091622575080900_B19","unstructured":"Gerstner, W.\n           (1998). Spiking neurons (Technical report). Cambridge, MA: MIT."},{"issue":"51","key":"2021091622575080900_B20","doi-asserted-by":"crossref","DOI":"10.21105\/joss.01989","article-title":"pylustrator: code generation for reproducible figures for publication","volume":"5","author":"Gerum","year":"2020","journal-title":"Journal of Open Source Software"},{"key":"2021091622575080900_B21","doi-asserted-by":"crossref","unstructured":"Gerum, R. C., Erpenbeck, A., Krauss, P., & Schilling, A. (2020). Sparsity through evolutionary pruning prevents neuronal networks from overfitting.Neural Networks, 128, 305\u2013312.","DOI":"10.1016\/j.neunet.2020.05.007"},{"key":"2021091622575080900_B22","doi-asserted-by":"crossref","DOI":"10.7554\/eLife.28295","article-title":"Predicting non-linear dynamics by stable local learning in a recurrent spiking neural network","volume":"6","author":"Gilra","year":"2017","journal-title":"eLife"},{"issue":"7","key":"2021091622575080900_B23","doi-asserted-by":"crossref","first-page":"558","DOI":"10.1106\/XC9U-BMJ8-FEIA-EUNQ","article-title":"Origins of activity patterns in self-organizing neuronal networks in vitro","volume":"10","author":"Gross","year":"1999","journal-title":"Journal of Intelligent Material Systems and Structures"},{"issue":"2","key":"2021091622575080900_B24","doi-asserted-by":"crossref","first-page":"245","DOI":"10.1016\/j.neuron.2017.06.011","article-title":"Neuroscience-inspired artificial intelligence","volume":"95","author":"Hassabis","year":"2017","journal-title":"Neuron"},{"key":"2021091622575080900_B25","doi-asserted-by":"crossref","DOI":"10.3389\/neuro.09.031.2009","article-title":"The human brain in numbers: A linearly scaled-up primate brain","volume":"3","author":"Herculano-Houzel","year":"2009","journal-title":"Frontiers in Human Neuroscience"},{"issue":"8","key":"2021091622575080900_B26","doi-asserted-by":"crossref","first-page":"1735","DOI":"10.1162\/neco.1997.9.8.1735","article-title":"Long short-term memory","volume":"9","author":"Hochreiter","year":"1997","journal-title":"Neural Computation"},{"issue":"4","key":"2021091622575080900_B27","doi-asserted-by":"crossref","first-page":"500","DOI":"10.1113\/jphysiol.1952.sp004764","article-title":"A quantitative description of membrane current and its application to conduction and excitation in nerve","volume":"117","author":"Hodgkin","year":"1952","journal-title":"Journal of Physiology"},{"key":"2021091622575080900_B28","first-page":"1433","volume-title":"Advances in neural information processing systems","author":"Huh","year":"2018"},{"issue":"3","key":"2021091622575080900_B29","doi-asserted-by":"crossref","first-page":"90","DOI":"10.1109\/MCSE.2007.55","article-title":"Matplotlib: A 2D graphics environment","volume":"9","author":"Hunter","year":"2007","journal-title":"Computing in Science and Engineering"},{"issue":"9","key":"2021091622575080900_B30","doi-asserted-by":"crossref","DOI":"10.4249\/scholarpedia.1349","article-title":"Fitzhugh-Nagumo model","volume":"1","author":"Izhikevich","year":"2006","journal-title":"Scholarpedia"},{"issue":"5","key":"2021091622575080900_B31","doi-asserted-by":"crossref","first-page":"91","DOI":"10.1109\/MCSE.2010.112","article-title":"Modeling spiking neural networks on spinnaker","volume":"12","author":"Jin","year":"2010","journal-title":"Computing in Science and Engineering"},{"key":"2021091622575080900_B32","doi-asserted-by":"crossref","unstructured":"Kheradpisheh, S. R., & Masquelier, T. (2019). S4nn: Temporal backpropagation for spiking neural networks with one spike per neuron. arXiv:1910.09495.","DOI":"10.1142\/S0129065720500276"},{"issue":"45","key":"2021091622575080900_B33","doi-asserted-by":"crossref","first-page":"22811","DOI":"10.1073\/pnas.1905926116","article-title":"Simple framework for constructing functional spiking recurrent neural networks","volume":"116","author":"Kim","year":"2019","journal-title":"Proceedings of the National Academy of Sciences"},{"key":"2021091622575080900_B34","unstructured":"Koch, C., & Segev, I. (Eds.). (1998). Methods in neuronal modeling: From ions to networksCambridge, MA: MIT Press."},{"key":"2021091622575080900_B35","unstructured":"Koopman, A., Van Leeuwen, M., & Vreeken, J. (2003). Dynamic neural networks, comparing spiking circuits and LSTM (Technical Report UU-CS-2003-007). Utrecht University."},{"issue":"1","key":"2021091622575080900_B36","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1038\/s41598-017-02644-w","article-title":"Adaptive stochastic resonance for unknown and variable input signals","volume":"7","author":"Krauss","year":"2017","journal-title":"Scientific Reports"},{"issue":"1","key":"2021091622575080900_B37","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1038\/s41598-018-23765-w","article-title":"A statistical method for analyzing and comparing spatiotemporal cortical activation patterns","volume":"8","author":"Krauss","year":"2018","journal-title":"Scientific Reports"},{"key":"2021091622575080900_B38","doi-asserted-by":"crossref","unstructured":"Krauss, P., Prebeck, K., Schilling, A., & Metzner, C. (2019). Recurrence resonance in three-neuron motifs.Frontiers in Computational Neuroscience, 13.","DOI":"10.3389\/fncom.2019.00064"},{"issue":"4","key":"2021091622575080900_B39","doi-asserted-by":"crossref","DOI":"10.1371\/journal.pone.0214541","article-title":"Weight statistics controls dynamics in recurrent neural networks","volume":"14","author":"Krauss","year":"2019","journal-title":"PLOS One"},{"key":"2021091622575080900_B40","doi-asserted-by":"crossref","DOI":"10.3389\/fnins.2016.00597","article-title":"Stochastic resonance controlled upregulation of internal noise after hearing loss as a putative cause of tinnitus-related neuronal hyperactivity","volume":"10","author":"Krauss","year":"2016","journal-title":"Frontiers in Neuroscience"},{"key":"2021091622575080900_B41","doi-asserted-by":"crossref","DOI":"10.3389\/fncom.2019.00005","article-title":"Analysis of structure and dynamics in three-neuron motifs","volume":"13","author":"Krauss","year":"2019","journal-title":"Frontiers in Computational Neuroscience"},{"issue":"9","key":"2021091622575080900_B42","doi-asserted-by":"crossref","first-page":"1148","DOI":"10.1038\/s41593-018-0210-5","article-title":"Cognitive computational neuroscience","volume":"21","author":"Kriegeskorte","year":"2018","journal-title":"Nature Neuroscience"},{"issue":"276","key":"2021091622575080900_B43","article-title":"Learning algorithms for classification: A comparison on handwritten digit recognition","volume":"261","author":"LeCun","year":"1995","journal-title":"Neural Networks"},{"key":"2021091622575080900_B44","doi-asserted-by":"crossref","unstructured":"Lee, C., Sarwar, S. S., Panda, P., Srinivasan, G., & Roy, K. (2020). Enabling spike-based backpropagation for training deep neural network architectures.Frontiers in Neuroscience, 14.","DOI":"10.3389\/fnins.2020.00119"},{"key":"2021091622575080900_B45","doi-asserted-by":"crossref","DOI":"10.3389\/fnins.2016.00508","article-title":"Training deep spiking neural networks using backpropagation","volume":"10","author":"Lee","year":"2016","journal-title":"Frontiers in Neuroscience"},{"issue":"10","key":"2021091622575080900_B46","doi-asserted-by":"crossref","first-page":"1414","DOI":"10.1016\/j.neuropsychologia.2003.12.016","article-title":"The neuropsychology of narrative: Story comprehension, story production and their interrelation","volume":"42","author":"Mar","year":"2004","journal-title":"Neuropsychologia"},{"key":"2021091622575080900_B47","doi-asserted-by":"crossref","first-page":"61","DOI":"10.1109\/MSP.2019.2931595","article-title":"Surrogate gradient learning in spiking neural networks","volume":"36","author":"Neftci","year":"2019","journal-title":"IEEE Signal Processing Magazine"},{"key":"2021091622575080900_B48","doi-asserted-by":"crossref","unstructured":"Nilsback, M.-E., & Zisserman, A. (2008). Automated flower classification over a large number of classes. In Proceedings of the 2008 Sixth Indian Conference on Computer Vision, Graphics and Image Processing (pp. 722\u2013729). Piscataway, NJ: IEEE.","DOI":"10.1109\/ICVGIP.2008.47"},{"key":"2021091622575080900_B49","doi-asserted-by":"crossref","unstructured":"Olshausen, B. A., & Field, D. J. (1997). Sparse coding with an overcomplete basis set: A strategy employed by V1?Vision Research, 37(23), 3311\u20133325.","DOI":"10.1016\/S0042-6989(97)00169-7"},{"key":"2021091622575080900_B50","doi-asserted-by":"crossref","DOI":"10.3389\/fnins.2015.00437","article-title":"Converting static image datasets to spiking neuromorphic datasets using saccades","volume":"9","author":"Orchard","year":"2015","journal-title":"Frontiers in Neuroscience"},{"key":"2021091622575080900_B51","unstructured":"Perkel, D. H., & Bullock, T. H. (1968). Neural coding.Neurosciences Research Program Bulletin, 6(3), 221\u2013348."},{"key":"2021091622575080900_B52","unstructured":"Pontes-Filho, S., & Nichele, S. (2019). Towards a framework for the evolution of artificial general intelligence. arXiv:1903.10410."},{"key":"2021091622575080900_B53","doi-asserted-by":"crossref","unstructured":"Pozzi, I., Nusselder, R., Zambrano, D., & Boht\u00e9, S. (2018). Gating sensory noise in a spiking subtractive LSTM. In Proceedings of the International Conference on Artificial Neural Networks (pp. 284\u2013293). Berlin: Springer.","DOI":"10.1007\/978-3-030-01418-6_28"},{"key":"2021091622575080900_B54","doi-asserted-by":"crossref","unstructured":"Qin, M., Xi, Y., & Jiang, F. (2019). A new improved convolutional neural network flower image recognition model. In Proceedings 2019 IEEE Symposium Series on Computational Intelligence (pp. 3110\u20133117). Piscataway, NJ: IEEE.","DOI":"10.1109\/SSCI44817.2019.9003016"},{"key":"2021091622575080900_B55","unstructured":"Rezaabad, A. L., & Vishwanath, S. (2020). Long short-term memory spiking networks and their applications. arXiv:2007.04779."},{"issue":"3","key":"2021091622575080900_B56","doi-asserted-by":"crossref","DOI":"10.1103\/RevModPhys.70.1027","article-title":"Single-photon detection by rod cells of the retina","volume":"70","author":"Rieke","year":"1998","journal-title":"Reviews of Modern Physics"},{"key":"2021091622575080900_B57","doi-asserted-by":"crossref","DOI":"10.7554\/eLife.59619","article-title":"Dendritic coincidence detection in Purkinje neurons of awake mice","volume":"9","author":"Roome","year":"2020","journal-title":"eLife"},{"key":"2021091622575080900_B58","doi-asserted-by":"crossref","DOI":"10.3389\/fnins.2017.00682","article-title":"Conversion of continuous-valued deep networks to efficient event-driven networks for image classification","volume":"11","author":"Rueckauer","year":"2017","journal-title":"Frontiers in Neuroscience"},{"issue":"3","key":"2021091622575080900_B59","doi-asserted-by":"crossref","first-page":"211","DOI":"10.1007\/s11263-015-0816-y","article-title":"ImageNet large scale visual recognition challenge","volume":"115","author":"Russakovsky","year":"2015","journal-title":"International Journal of Computer Vision"},{"key":"2021091622575080900_B60","doi-asserted-by":"crossref","unstructured":"Schemmel, J., Grubl, A., Meier, K., & Mueller, E. (2006). Implementing synaptic plasticity in a VLSI spiking neural network model. In Proceedings of the 2006 IEEE International Joint Conference on Neural Network Proceedings (pp. 1\u20136). Piscataway, NJ: IEEE.","DOI":"10.1109\/IJCNN.2006.246651"},{"key":"2021091622575080900_B61","doi-asserted-by":"crossref","unstructured":"Schilling, A., Gerum, R., Zankl, A., Schulze, H., Metzner, C., & Krauss, P. (2020). Intrinsic noise improves speech recognition in a computational model of the auditory pathway. bioRxiv.","DOI":"10.1101\/2020.03.16.993725"},{"key":"2021091622575080900_B62","unstructured":"Schrauwen, B., & Van Campenhout, J. (2004a). Extending SpikeProp. In Proceedings of the 2004 IEEE International Joint Conference on Neural Networks (pp. 471\u2013475). Piscataway, NJ: IEEE."},{"key":"2021091622575080900_B63","unstructured":"Schrauwen, B., & Van Campenhout, J. (2004b). Improving SpikeProp: Enhancements to an error-backpropagation rule for spiking neural networks. In Proceedings of the 15th ProRISC Workshop, 11 (pp. 301\u2013305)."},{"issue":"14","key":"2021091622575080900_B64","doi-asserted-by":"crossref","first-page":"1025","DOI":"10.1016\/j.scib.2017.06.007","article-title":"Distributed secure quantum machine learning","volume":"62","author":"Sheng","year":"2017","journal-title":"Science Bulletin"},{"issue":"10","key":"2021091622575080900_B65","doi-asserted-by":"crossref","first-page":"e49177","DOI":"10.15252\/embr.201949177","article-title":"The limits of machine intelligence: Despite progress in machine intelligence, artificial general intelligence is still a major challenge","volume":"20","author":"Shevlin","year":"2019","journal-title":"EMBO Reports"},{"key":"2021091622575080900_B66","first-page":"1412","volume-title":"Advances in neural information processing systems","author":"Shrestha","year":"2018"},{"key":"2021091622575080900_B67","doi-asserted-by":"crossref","unstructured":"Steinkraus, D., Buck, I., & Simard, P. (2005). Using GPUs for machine learning algorithms. In Proceedings of the Eighth International Conference on Document Analysis and Recognition (pp. 1115\u20131120). Piscataway, NJ: IEEE.","DOI":"10.1109\/ICDAR.2005.251"},{"key":"2021091622575080900_B68","doi-asserted-by":"crossref","first-page":"253","DOI":"10.1016\/j.neunet.2019.09.036","article-title":"A review of learning in biologically plausible spiking neural networks","volume":"122","author":"Taherkhani","year":"2020","journal-title":"Neural Networks"},{"key":"2021091622575080900_B69","doi-asserted-by":"crossref","first-page":"47","DOI":"10.1016\/j.neunet.2018.12.002","article-title":"Deep learning in spiking neural networks","volume":"111","author":"Tavanaei","year":"2019","journal-title":"Neural Networks"},{"issue":"7","key":"2021091622575080900_B70","doi-asserted-by":"crossref","first-page":"309","DOI":"10.1016\/j.tics.2006.05.009","article-title":"Theory-based Bayesian models of inductive learning and reasoning","volume":"10","author":"Tenenbaum","year":"2006","journal-title":"Trends in Cognitive Sciences"},{"issue":"6-7","key":"2021091622575080900_B71","doi-asserted-by":"crossref","first-page":"715","DOI":"10.1016\/S0893-6080(01)00083-1","article-title":"Spike-based strategies for rapid processing","volume":"14","author":"Thorpe","year":"2001","journal-title":"Neural Networks"},{"key":"2021091622575080900_B72","unstructured":"Vreeken, J.\n           (2003). Spiking neural networks, an introduction. (Technical Report UU-CS-2003-008). Utrect University."},{"issue":"2","key":"2021091622575080900_B73","doi-asserted-by":"crossref","first-page":"22","DOI":"10.1109\/MCSE.2011.37","article-title":"The NumPy array: A structure for efficient numerical computation","volume":"13","author":"Walt","year":"2011","journal-title":"Computing in Science and Engineering"},{"issue":"12","key":"2021091622575080900_B74","doi-asserted-by":"crossref","first-page":"1760","DOI":"10.1038\/nn1591","article-title":"Synaptic background activity controls spike transfer from thalamus to cortex","volume":"8","author":"Wolfart","year":"2005","journal-title":"Nature Neuroscience"},{"key":"2021091622575080900_B75","doi-asserted-by":"crossref","unstructured":"Wu, Y., Deng, L., Li, G., Zhu, J., & Shi, L. (2018). Spatio-temporal backpropagation for training high-performance spiking neural networks.Frontiers in Neuroscience, 12:331.","DOI":"10.3389\/fnins.2018.00331"},{"key":"2021091622575080900_B76","unstructured":"Xia, X., Xu, C., & Nan, B. (2017). Inception-v3 for flower classification. In Proceedings of the 2nd International Conference on Image, Vision and Computing (pp. 783\u2013787). Piscataway, IEEE."},{"key":"2021091622575080900_B77","unstructured":"Xin, J., & Embrechts, M. J. (2001). Supervised learning with spiking neural networks. In Proceedings of the International Joint Conference on Neural Networks. Proceedings (pp. 1772\u20131777). Piscataway, NJ: IEEE."},{"key":"2021091622575080900_B78","doi-asserted-by":"crossref","unstructured":"Yang, Z., Schilling, A., Maier, A., & Krauss, P. (2021). Neural networks with fixed binary random projections improve accuracy in classifying noisy data. In Bildverarbeitung f\u00fcr die Medizin (pp. 211\u2013216). Berlin: Springer.","DOI":"10.1007\/978-3-658-33198-6_51"},{"issue":"6","key":"2021091622575080900_B79","doi-asserted-by":"crossref","first-page":"1514","DOI":"10.1162\/neco_a_01086","article-title":"SuperSpike: Supervised learning in multilayer spiking neural networks","volume":"30","author":"Zenke","year":"2018","journal-title":"Neural Computation"},{"key":"2021091622575080900_B80","doi-asserted-by":"crossref","DOI":"10.3389\/fninf.2014.00076","article-title":"Limits to high-speed simulations of spiking neural networks using general-purpose computers","volume":"8","author":"Zenke","year":"2014","journal-title":"Frontiers in Neuroinformatics"},{"key":"2021091622575080900_B81","doi-asserted-by":"crossref","unstructured":"Zenke, F., & Vogels, T. P. (2020). The remarkable robustness of surrogate gradient learning for instilling complex function in spiking neural networks.BioRxiv.","DOI":"10.1101\/2020.06.29.176925"}],"container-title":["Neural Computation"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/direct.mit.edu\/neco\/article-pdf\/33\/10\/2827\/1963343\/neco_a_01424.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"http:\/\/direct.mit.edu\/neco\/article-pdf\/33\/10\/2827\/1963343\/neco_a_01424.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,9,16]],"date-time":"2021-09-16T22:59:30Z","timestamp":1631833170000},"score":1,"resource":{"primary":{"URL":"https:\/\/direct.mit.edu\/neco\/article\/33\/10\/2827\/103010\/Integration-of-Leaky-Integrate-and-Fire-Neurons-in"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,9,16]]},"references-count":81,"journal-issue":{"issue":"10","published-online":{"date-parts":[[2021,9,16]]},"published-print":{"date-parts":[[2021,9,16]]}},"URL":"https:\/\/doi.org\/10.1162\/neco_a_01424","relation":{},"ISSN":["0899-7667","1530-888X"],"issn-type":[{"value":"0899-7667","type":"print"},{"value":"1530-888X","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2021,10]]},"published":{"date-parts":[[2021,9,16]]}}}