Cargando…
Presynaptic spike-driven plasticity based on eligibility trace for on-chip learning system
INTRODUCTION: Recurrent spiking neural network (RSNN) performs excellently in spatio-temporal learning with backpropagation through time (BPTT) algorithm. But the requirement of computation and memory in BPTT makes it hard to realize an on-chip learning system based on RSNN. In this paper, we aim to...
Autores principales: | Gao, Tian, Deng, Bin, Wang, Jiang, Yi, Guosheng |
---|---|
Formato: | Online Artículo Texto |
Lenguaje: | English |
Publicado: |
Frontiers Media S.A.
2023
|
Materias: | |
Acceso en línea: | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9997725/ https://www.ncbi.nlm.nih.gov/pubmed/36908804 http://dx.doi.org/10.3389/fnins.2023.1107089 |
Ejemplares similares
-
Highly efficient neuromorphic learning system of spiking neural network with multi-compartment leaky integrate-and-fire neurons
por: Gao, Tian, et al.
Publicado: (2022) -
Efficient Spike-Driven Learning With Dendritic Event-Based Processing
por: Yang, Shuangming, et al.
Publicado: (2021) -
Eligibility Traces and Plasticity on Behavioral Time Scales: Experimental Support of NeoHebbian Three-Factor Learning Rules
por: Gerstner, Wulfram, et al.
Publicado: (2018) -
Presynaptic long-term plasticity
por: Yang, Ying, et al.
Publicado: (2013) -
One-shot learning and behavioral eligibility traces in sequential decision making
por: Lehmann, Marco P, et al.
Publicado: (2019)