{"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/spiking-deep-networks-with-lif-neurons","title":"Spiking Deep Networks with LIF Neurons","arxiv_id":"1510.08829","date":"2015-10-29","proceeding":null,"authors":["Eric Hunsberger","Chris Eliasmith"],"abstract":"We train spiking deep networks using leaky integrate-and-fire (LIF) neurons,\nand achieve state-of-the-art results for spiking networks on the CIFAR-10 and\nMNIST datasets. This demonstrates that biologically-plausible spiking LIF\nneurons can be integrated into deep networks can perform as well as other\nspiking models (e.g. integrate-and-fire). We achieved this result by softening\nthe LIF response function, such that its derivative remains bounded, and by\ntraining the network with noise to provide robustness against the variability\nintroduced by spikes. Our method is general and could be applied to other\nneuron types, including those used on modern neuromorphic hardware. Our work\nbrings more biological realism into modern image classification models, with\nthe hope that these models can inform how the brain performs this difficult\ntask. It also provides new methods for training deep networks to run on\nneuromorphic hardware, with the aim of fast, power-efficient image\nclassification for robotics applications.","url_abs":"http://arxiv.org/abs/1510.08829v1","url_pdf":"http://arxiv.org/pdf/1510.08829v1.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":"spiking-deep-networks-with-lif-neurons","repo_url":"https://github.com/Brain-Inspired-Computing/Final-Project","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok"}},{"paper_slug":"spiking-deep-networks-with-lif-neurons","repo_url":"https://github.com/MarcoSaku/Spiking-C3D","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok"}}],"tasks":[{"task_slug":"classification","task_name":"General Classification"},{"task_slug":"image-classification","task_name":"Image Classification"},{"task_slug":"image-classification","task_name":"image-classification"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/1510.08829","atlas_url":"https://app.syntology.ai/?focus=1510.08829","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}