{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/hybrid-macromicro-level-backpropagation-for","title":"Hybrid Macro/Micro Level Backpropagation for Training Deep Spiking Neural Networks","arxiv_id":"1805.07866","date":"2018-05-21","proceeding":"NeurIPS 2018 12","authors":["Yingyezhe Jin","Wenrui Zhang","Peng Li"],"abstract":"Spiking neural networks (SNNs) are positioned to enable spatio-temporal\ninformation processing and ultra-low power event-driven neuromorphic hardware.\nHowever, SNNs are yet to reach the same performances of conventional deep\nartificial neural networks (ANNs), a long-standing challenge due to complex\ndynamics and non-differentiable spike events encountered in training. The\nexisting SNN error backpropagation (BP) methods are limited in terms of\nscalability, lack of proper handling of spiking discontinuities, and/or\nmismatch between the rate-coded loss function and computed gradient. We present\na hybrid macro/micro level backpropagation (HM2-BP) algorithm for training\nmulti-layer SNNs. The temporal effects are precisely captured by the proposed\nspike-train level post-synaptic potential (S-PSP) at the microscopic level. The\nrate-coded errors are defined at the macroscopic level, computed and\nback-propagated across both macroscopic and microscopic levels. Different from\nexisting BP methods, HM2-BP directly computes the gradient of the rate-coded\nloss function w.r.t tunable parameters. We evaluate the proposed HM2-BP\nalgorithm by training deep fully connected and convolutional SNNs based on the\nstatic MNIST [14] and dynamic neuromorphic N-MNIST [26]. HM2-BP achieves an\naccuracy level of 99.49% and 98.88% for MNIST and N-MNIST, respectively,\noutperforming the best reported performances obtained from the existing SNN BP\nalgorithms. Furthermore, the HM2-BP produces the highest accuracies based on\nSNNs for the EMNIST [3] dataset, and leads to high recognition accuracy for the\n16-speaker spoken English letters of TI46 Corpus [16], a challenging\npatio-temporal speech recognition benchmark for which no prior success based on\nSNNs was reported. It also achieves competitive performances surpassing those\nof conventional deep learning models when dealing with asynchronous spiking\nstreams.","url_abs":"http://arxiv.org/abs/1805.07866v6","url_pdf":"http://arxiv.org/pdf/1805.07866v6.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"hybrid-macromicro-level-backpropagation-for","repo_url":"https://github.com/jinyyy666/mm-bp-snn","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok"}}],"tasks":[{"task_slug":"image-classification","task_name":"Image Classification"},{"task_slug":"speech-recognition","task_name":"Speech Recognition"},{"task_slug":"speech-recognition-1","task_name":"speech-recognition"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/image-classification-on-emnist-balanced","task":"Image Classification","dataset":"EMNIST-Balanced","model":"HM2-BP","rank_in_archive_order":13,"of":20,"metrics":{"Accuracy":"85.57","Trainable Parameters":"665647"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/1805.07866","atlas_url":"https://app.syntology.ai/?focus=1805.07866","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}