Cargando…
Learning cortical hierarchies with temporal Hebbian updates
A key driver of mammalian intelligence is the ability to represent incoming sensory information across multiple abstraction levels. For example, in the visual ventral stream, incoming signals are first represented as low-level edge filters and then transformed into high-level object representations....
Autores principales: | Aceituno, Pau Vilimelis, Farinha, Matilde Tristany, Loidl, Reinhard, Grewe, Benjamin F. |
---|---|
Formato: | Online Artículo Texto |
Lenguaje: | English |
Publicado: |
Frontiers Media S.A.
2023
|
Materias: | |
Acceso en línea: | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10244748/ https://www.ncbi.nlm.nih.gov/pubmed/37293353 http://dx.doi.org/10.3389/fncom.2023.1136010 |
Ejemplares similares
-
Bio-inspired, task-free continual learning through activity regularization
por: Lässig, Francesco, et al.
Publicado: (2023) -
Deep Learning With Asymmetric Connections and Hebbian Updates
por: Amit, Yali
Publicado: (2019) -
Deep Gated Hebbian Predictive Coding Accounts for Emergence of Complex Neural Response Properties Along the Visual Cortical Hierarchy
por: Dora, Shirin, et al.
Publicado: (2021) -
Learning to Generate Sequences with Combination of Hebbian and Non-hebbian Plasticity in Recurrent Spiking Neural Networks
por: Panda, Priyadarshini, et al.
Publicado: (2017) -
Tailoring Echo State Networks for Optimal Learning
por: Aceituno, Pau Vilimelis, et al.
Publicado: (2020)