2026-05-17T23:26:55Zhttps://www.bilketa.eus/in/rest/oai

oai:www.bilketa.eus:ark:/27020/hal-02460417ALL2025-06-05T09:20:18Z

https://www.bilketa.eus/ark:/27020/hal-02460417Tecnalia [Derio]Tecnalia [Derio]Basque Center for Applied Mathematics (BCAM) ; Basque Center for Applied MathematicsUniversidad del País Vasco / Euskal Herriko Unibertsitatea (UPV / EHU)Data, Intelligence and Graphs (DIG) ; Laboratoire Traitement et Communication de l'Information (LTCI) ; Institut Mines-Télécom [Paris] (IMT)-Télécom Paris ; Institut Mines-Télécom [Paris] (IMT)-Institut Polytechnique de Paris (IP Paris)-Institut Polytechnique de Paris (IP Paris)-Institut Mines-Télécom [Paris] (IMT)-Télécom Paris ; Institut Mines-Télécom [Paris] (IMT)-Institut Polytechnique de Paris (IP Paris)-Institut Polytechnique de Paris (IP Paris)Département Informatique et Réseaux (INFRES) ; Télécom ParisTechKnowledge Engineering and Discovery Research Institute ; Auckland University of Technology (AUT)Lobo, Jesusdel Ser, JavierBifet, AlbertKasabov, NikolaHAL, hal-024604172020-01International audienceApplications that generate huge amounts of data in the form of fast streams are becoming increasingly prevalent, being therefore necessary to learn in an online manner. These conditions usually impose memory and processing time restrictions, and they often turn into evolving environments where a change may affect the input data distribution. Such a change causes that predictive models trained over these stream data become obsolete and do not adapt suitably to new distributions. Specially in these non-stationary scenarios, there is a pressing need for new algorithms that adapt to these changes as fast as possible, while maintaining good performance scores. Unfortunately, most off-the-shelf classification models need to be retrained if they are used in changing environments, and fail to scale properly. Spiking Neural Networks have revealed themselves as one of the most successful approaches to model the behavior and learning potential of the brain, and exploit them to undertake practical online learning tasks. Besides, some specific flavors of Spiking Neural Networks can overcome the necessity of retraining after a drift occurs. This work intends to merge both fields by serving as a comprehensive overview, motivating further developments that embrace Spiking Neural Networks for online learning scenarios, and being a friendly entry point for non-experts.https://hal.science/hal-02460417https://telecom-paris.hal.science/hal-02460417v1/file/1908.08019.pdfArticle de journal | Aldizkari bateko artikuluavignette : https://www.bilketa.eus/in/rest/Thumb/image?id=ark:/27020/hal-02460417&mat=articleNumengArchive ouverte HAL | HAL artxibo irekiaOnline learningSpiking Neural NetworksStream dataConcept drift[INFO.INFO-AI]Computer Science [cs]/Artificial Intelligence [cs.AI]Spiking Neural Networks and online learning: An overview and perspectives