{"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/s-tllr-stdp-inspired-temporal-local-learning","title":"S-TLLR: STDP-inspired Temporal Local Learning Rule for Spiking Neural Networks","arxiv_id":"2306.15220","date":"2023-06-27","proceeding":null,"authors":["Marco Paul E. Apolinario","Kaushik Roy"],"abstract":"Spiking Neural Networks (SNNs) are biologically plausible models that have been identified as potentially apt for deploying energy-efficient intelligence at the edge, particularly for sequential learning tasks. However, training of SNNs poses significant challenges due to the necessity for precise temporal and spatial credit assignment. Back-propagation through time (BPTT) algorithm, whilst the most widely used method for addressing these issues, incurs high computational cost due to its temporal dependency. In this work, we propose S-TLLR, a novel three-factor temporal local learning rule inspired by the Spike-Timing Dependent Plasticity (STDP) mechanism, aimed at training deep SNNs on event-based learning tasks. Furthermore, S-TLLR is designed to have low memory and time complexities, which are independent of the number of time steps, rendering it suitable for online learning on low-power edge devices. To demonstrate the scalability of our proposed method, we have conducted extensive evaluations on event-based datasets spanning a wide range of applications, such as image and gesture recognition, audio classification, and optical flow estimation. In all the experiments, S-TLLR achieved high accuracy, comparable to BPTT, with a reduction in memory between $5-50\\times$ and multiply-accumulate (MAC) operations between $1.3-6.6\\times$.","url_abs":"https://arxiv.org/abs/2306.15220v4","url_pdf":"https://arxiv.org/pdf/2306.15220v4.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":"s-tllr-stdp-inspired-temporal-local-learning","repo_url":"https://github.com/mapolinario94/s-tllr","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"audio-classification","task_name":"Audio Classification"},{"task_slug":"event-based-optical-flow","task_name":"Event-based Optical Flow"},{"task_slug":"gesture-recognition","task_name":"Gesture Recognition"},{"task_slug":"image-classification","task_name":"Image Classification"},{"task_slug":"optical-flow-estimation","task_name":"Optical Flow Estimation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/event-based-optical-flow-on-mvsec","task":"Event-based Optical Flow","dataset":"MVSEC","model":"S-TLLR","rank_in_archive_order":1,"of":1,"metrics":{"Average End-Point Error":"3.45"},"uses_additional_data":false},{"leaderboard":"/sota/gesture-recognition-on-dvs128-gesture","task":"Gesture Recognition","dataset":"DVS128 Gesture","model":"S-TLLR","rank_in_archive_order":5,"of":14,"metrics":{"Accuracy (%)":"97.72"},"uses_additional_data":false},{"leaderboard":"/sota/image-classification-on-n-caltech-101","task":"Image Classification","dataset":"N-Caltech 101","model":"S-TLLR","rank_in_archive_order":2,"of":3,"metrics":{"Accuracy":"66.05"},"uses_additional_data":false}],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}