SoftHebb: Bayesian inference in unsupervised Hebbian soft winner-take-all networks

Hebbian plasticity in winner-take-all (WTA) networks is highly attractive for neuromorphic on-chip learning, owing to its efficient, local, unsupervised, and on-line nature. Moreover, its biological plausibility may help overcome important limitations of artificial algorithms, such as their suscepti...

Descripció completa

Dades bibliogràfiques

Autors principals:	Timoleon Moraitis, Dmitry Toichkin, Adrien Journé, Yansong Chua, Qinghai Guo
Format:	Artigo
Idioma:	Inglês
Publicat:	IOP Publishing 2022-01-01
Col·lecció:	Neuromorphic Computing and Engineering
Matèries:	adversarial robustness local plasticity alternative to backpropagation neuromorphic efficiency Bayesian generative model online unsupervised Hebbian learning
Accés en línia:	https://doi.org/10.1088/2634-4386/aca710
Etiquetes:	Afegir etiqueta Sense etiquetes, Sigues el primer a etiquetar aquest registre!