{"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/slayer-spike-layer-error-reassignment-in-time","title":"SLAYER: Spike Layer Error Reassignment in Time","arxiv_id":"1810.08646","date":"2018-09-05","proceeding":"NeurIPS 2018 12","authors":["Sumit Bam Shrestha","Garrick Orchard"],"abstract":"Configuring deep Spiking Neural Networks (SNNs) is an exciting research\navenue for low power spike event based computation. However, the spike\ngeneration function is non-differentiable and therefore not directly compatible\nwith the standard error backpropagation algorithm. In this paper, we introduce\na new general backpropagation mechanism for learning synaptic weights and\naxonal delays which overcomes the problem of non-differentiability of the spike\nfunction and uses a temporal credit assignment policy for backpropagating error\nto preceding layers. We describe and release a GPU accelerated software\nimplementation of our method which allows training both fully connected and\nconvolutional neural network (CNN) architectures. Using our software, we\ncompare our method against existing SNN based learning approaches and standard\nANN to SNN conversion techniques and show that our method achieves state of the\nart performance for an SNN on the MNIST, NMNIST, DVS Gesture, and TIDIGITS\ndatasets.","url_abs":"http://arxiv.org/abs/1810.08646v1","url_pdf":"http://arxiv.org/pdf/1810.08646v1.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":"slayer-spike-layer-error-reassignment-in-time","repo_url":"https://bitbucket.org/bamsumit/slayer","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"slayer-spike-layer-error-reassignment-in-time","repo_url":"https://github.com/bamsumit/slayerPytorch","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"GPL-3.0"}}],"tasks":[{"task_slug":null,"task_name":"GPU"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1810.08646","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}