{"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/spatio-temporal-backpropagation-for-training","title":"Spatio-Temporal Backpropagation for Training High-performance Spiking Neural Networks","arxiv_id":"1706.02609","date":"2017-06-08","proceeding":null,"authors":["Yujie Wu","Lei Deng","Guoqi Li","Jun Zhu","Luping Shi"],"abstract":"Compared with artificial neural networks (ANNs), spiking neural networks\n(SNNs) are promising to explore the brain-like behaviors since the spikes could\nencode more spatio-temporal information. Although pre-training from ANN or\ndirect training based on backpropagation (BP) makes the supervised training of\nSNNs possible, these methods only exploit the networks' spatial domain\ninformation which leads to the performance bottleneck and requires many\ncomplicated training skills. Another fundamental issue is that the spike\nactivity is naturally non-differentiable which causes great difficulties in\ntraining SNNs. To this end, we build an iterative LIF model that is more\nfriendly for gradient descent training. By simultaneously considering the\nlayer-by-layer spatial domain (SD) and the timing-dependent temporal domain\n(TD) in the training phase, as well as an approximated derivative for the spike\nactivity, we propose a spatio-temporal backpropagation (STBP) training\nframework without using any complicated technology. We achieve the best\nperformance of multi-layered perceptron (MLP) compared with existing\nstate-of-the-art algorithms over the static MNIST and the dynamic N-MNIST\ndataset as well as a custom object detection dataset. This work provides a new\nperspective to explore the high-performance SNNs for future brain-like\ncomputing paradigm with rich spatio-temporal dynamics.","url_abs":"http://arxiv.org/abs/1706.02609v3","url_pdf":"http://arxiv.org/pdf/1706.02609v3.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":"spatio-temporal-backpropagation-for-training","repo_url":"https://github.com/albertopolito/CarSNN","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"object-detection","task_name":"Object Detection"},{"task_slug":"high","task_name":"Vocal Bursts Intensity Prediction"},{"task_slug":"object-detection-1","task_name":"object-detection"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1706.02609","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}