Somatodendritic consistency check for temporal feature segmentation

The authors propose a learning rule for a neuron model with dendrite. In their model, somatodendritic interaction implements self-supervised learning applicable to a wide range of sequence learning tasks, including spike pattern detection, chunking temporal input and blind source separation.

Guardado en:
Detalles Bibliográficos
Autores principales: Toshitake Asabuki, Tomoki Fukai
Formato: article
Lenguaje:EN
Publicado: Nature Portfolio 2020
Materias:
Q
Acceso en línea:https://doaj.org/article/bca74058d2934f1ea7f00b93a28b4a33
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
Descripción
Sumario:The authors propose a learning rule for a neuron model with dendrite. In their model, somatodendritic interaction implements self-supervised learning applicable to a wide range of sequence learning tasks, including spike pattern detection, chunking temporal input and blind source separation.