{"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/scalable-event-by-event-processing-of","title":"Scalable Event-by-event Processing of Neuromorphic Sensory Signals With Deep State-Space Models","arxiv_id":"2404.18508","date":"2024-04-29","proceeding":null,"authors":["Mark Schöne","Neeraj Mohan Sushma","Jingyue Zhuge","Christian Mayr","Anand Subramoney","David Kappel"],"abstract":"Event-based sensors are well suited for real-time processing due to their fast response times and encoding of the sensory data as successive temporal differences. These and other valuable properties, such as a high dynamic range, are suppressed when the data is converted to a frame-based format. However, most current methods either collapse events into frames or cannot scale up when processing the event data directly event-by-event. In this work, we address the key challenges of scaling up event-by-event modeling of the long event streams emitted by such sensors, which is a particularly relevant problem for neuromorphic computing. While prior methods can process up to a few thousand time steps, our model, based on modern recurrent deep state-space models, scales to event streams of millions of events for both training and inference. We leverage their stable parameterization for learning long-range dependencies, parallelizability along the sequence dimension, and their ability to integrate asynchronous events effectively to scale them up to long event streams. We further augment these with novel event-centric techniques enabling our model to match or beat the state-of-the-art performance on several event stream benchmarks. In the Spiking Speech Commands task, we improve state-of-the-art by a large margin of 7.7% to 88.4%. On the DVS128-Gestures dataset, we achieve competitive results without using frames or convolutional neural networks. Our work demonstrates, for the first time, that it is possible to use fully event-based processing with purely recurrent networks to achieve state-of-the-art task performance in several event-based benchmarks.","url_abs":"https://arxiv.org/abs/2404.18508v3","url_pdf":"https://arxiv.org/pdf/2404.18508v3.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":"scalable-event-by-event-processing-of","repo_url":"https://github.com/Efficient-Scalable-Machine-Learning/event-ssm","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"jax","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"audio-classification","task_name":"Audio Classification"},{"task_slug":"gesture-recognition","task_name":"Gesture Recognition"},{"task_slug":"hand-gesture-recognition-1","task_name":"Hand-Gesture Recognition"},{"task_slug":"state-space-models","task_name":"State Space Models"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/audio-classification-on-shd","task":"Audio Classification","dataset":"SHD","model":"Event-SSM","rank_in_archive_order":1,"of":11,"metrics":{"Percentage correct":"95.9"},"uses_additional_data":false},{"leaderboard":"/sota/audio-classification-on-ssc","task":"Audio Classification","dataset":"SSC","model":"Event-SSM","rank_in_archive_order":1,"of":5,"metrics":{"Accuracy":"88.4"},"uses_additional_data":false},{"leaderboard":"/sota/gesture-recognition-on-dvs128-gesture","task":"Gesture Recognition","dataset":"DVS128 Gesture","model":"Event-SSM","rank_in_archive_order":6,"of":14,"metrics":{"Accuracy (%)":"97.7"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2404.18508","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2404.18508"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/Efficient-Scalable-Machine-Learning/event-ssm","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran":15,"unverified":3},"by_repo_kind":{"official":{"samples":18,"ran":15,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":0,"samples":[{"code_sha256_prefix":"801be17d5a9e3d5d","entry":"cut_mix_augmentation","repo":"Efficient-Scalable-Machine-Learning/event-ssm","repo_kind":"official","path":"event_ssm/transform.py","file_url":"https://github.com/Efficient-Scalable-Machine-Learning/event-ssm/blob/HEAD/event_ssm/transform.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"801be17d5a9e3d5d"}},{"code_sha256_prefix":"878ef192b1e8192e","entry":"cut_mix_augmentation_time","repo":"Efficient-Scalable-Machine-Learning/event-ssm","repo_kind":"official","path":"event_ssm/transform.py","file_url":"https://github.com/Efficient-Scalable-Machine-Learning/event-ssm/blob/HEAD/event_ssm/transform.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"878ef192b1e8192e"}},{"code_sha256_prefix":"9e888aab5e750287","entry":"discretize_dirac","repo":"Efficient-Scalable-Machine-Learning/event-ssm","repo_kind":"official","path":"event_ssm/ssm.py","file_url":"https://github.com/Efficient-Scalable-Machine-Learning/event-ssm/blob/HEAD/event_ssm/ssm.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"9e888aab5e750287"}},{"code_sha256_prefix":"bb3aeee6201c06dd","entry":"discretize_zoh","repo":"Efficient-Scalable-Machine-Learning/event-ssm","repo_kind":"official","path":"event_ssm/ssm.py","file_url":"https://github.com/Efficient-Scalable-Machine-Learning/event-ssm/blob/HEAD/event_ssm/ssm.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"bb3aeee6201c06dd"}},{"code_sha256_prefix":"7905962f8670b1da","entry":"evaluation_step","repo":"Efficient-Scalable-Machine-Learning/event-ssm","repo_kind":"official","path":"event_ssm/train_utils.py","file_url":"https://github.com/Efficient-Scalable-Machine-Learning/event-ssm/blob/HEAD/event_ssm/train_utils.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"7905962f8670b1da"}},{"code_sha256_prefix":"1b34fdae353a499d","entry":"evaluation_step","repo":"Efficient-Scalable-Machine-Learning/event-ssm","repo_kind":"official","path":"run_evaluation.py","file_url":"https://github.com/Efficient-Scalable-Machine-Learning/event-ssm/blob/HEAD/run_evaluation.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"1b34fdae353a499d"}},{"code_sha256_prefix":"e0293591386f80aa","entry":"event_stream_dataloader","repo":"Efficient-Scalable-Machine-Learning/event-ssm","repo_kind":"official","path":"event_ssm/dataloading.py","file_url":"https://github.com/Efficient-Scalable-Machine-Learning/event-ssm/blob/HEAD/event_ssm/dataloading.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"e0293591386f80aa"}},{"code_sha256_prefix":"188626e586495ec6","entry":"make_DPLR_HiPPO","repo":"Efficient-Scalable-Machine-Learning/event-ssm","repo_kind":"official","path":"event_ssm/ssm_init.py","file_url":"https://github.com/Efficient-Scalable-Machine-Learning/event-ssm/blob/HEAD/event_ssm/ssm_init.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"188626e586495ec6"}},{"code_sha256_prefix":"27e9e05de680bfb5","entry":"make_HiPPO","repo":"Efficient-Scalable-Machine-Learning/event-ssm","repo_kind":"official","path":"event_ssm/ssm_init.py","file_url":"https://github.com/Efficient-Scalable-Machine-Learning/event-ssm/blob/HEAD/event_ssm/ssm_init.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"27e9e05de680bfb5"}},{"code_sha256_prefix":"17177c94dcd9bfbf","entry":"make_NPLR_HiPPO","repo":"Efficient-Scalable-Machine-Learning/event-ssm","repo_kind":"official","path":"event_ssm/ssm_init.py","file_url":"https://github.com/Efficient-Scalable-Machine-Learning/event-ssm/blob/HEAD/event_ssm/ssm_init.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"17177c94dcd9bfbf"}},{"code_sha256_prefix":"50b98382b2de060e","entry":"map_nested_fn","repo":"Efficient-Scalable-Machine-Learning/event-ssm","repo_kind":"official","path":"event_ssm/train_utils.py","file_url":"https://github.com/Efficient-Scalable-Machine-Learning/event-ssm/blob/HEAD/event_ssm/train_utils.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"50b98382b2de060e"}},{"code_sha256_prefix":"f2a2429ab2b145a5","entry":"masked_meanpool","repo":"Efficient-Scalable-Machine-Learning/event-ssm","repo_kind":"official","path":"event_ssm/seq_model.py","file_url":"https://github.com/Efficient-Scalable-Machine-Learning/event-ssm/blob/HEAD/event_ssm/seq_model.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"f2a2429ab2b145a5"}},{"code_sha256_prefix":"d0d2c7cc8a0e8597","entry":"reshape_array_per_device","repo":"Efficient-Scalable-Machine-Learning/event-ssm","repo_kind":"official","path":"event_ssm/trainer.py","file_url":"https://github.com/Efficient-Scalable-Machine-Learning/event-ssm/blob/HEAD/event_ssm/trainer.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"d0d2c7cc8a0e8597"}},{"code_sha256_prefix":"0512fd084f8551e4","entry":"reshape_batch_per_device","repo":"Efficient-Scalable-Machine-Learning/event-ssm","repo_kind":"official","path":"event_ssm/trainer.py","file_url":"https://github.com/Efficient-Scalable-Machine-Learning/event-ssm/blob/HEAD/event_ssm/trainer.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"0512fd084f8551e4"}},{"code_sha256_prefix":"b03910f5f285bbc7","entry":"timepool","repo":"Efficient-Scalable-Machine-Learning/event-ssm","repo_kind":"official","path":"event_ssm/seq_model.py","file_url":"https://github.com/Efficient-Scalable-Machine-Learning/event-ssm/blob/HEAD/event_ssm/seq_model.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"b03910f5f285bbc7"}},{"code_sha256_prefix":"b84da31f714379cb","entry":"discretize_async","repo":"Efficient-Scalable-Machine-Learning/event-ssm","repo_kind":"official","path":"event_ssm/ssm.py","file_url":"https://github.com/Efficient-Scalable-Machine-Learning/event-ssm/blob/HEAD/event_ssm/ssm.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"b84da31f714379cb"}},{"code_sha256_prefix":"de3055769b640635","entry":"masked_timepool","repo":"Efficient-Scalable-Machine-Learning/event-ssm","repo_kind":"official","path":"event_ssm/seq_model.py","file_url":"https://github.com/Efficient-Scalable-Machine-Learning/event-ssm/blob/HEAD/event_ssm/seq_model.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"de3055769b640635"}},{"code_sha256_prefix":"5f8147f4c2b3b6c4","entry":"training_step","repo":"Efficient-Scalable-Machine-Learning/event-ssm","repo_kind":"official","path":"event_ssm/train_utils.py","file_url":"https://github.com/Efficient-Scalable-Machine-Learning/event-ssm/blob/HEAD/event_ssm/train_utils.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"5f8147f4c2b3b6c4"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}