Cargando…
Optimizing BCPNN Learning Rule for Memory Access
Simulation of large scale biologically plausible spiking neural networks, e.g., Bayesian Confidence Propagation Neural Network (BCPNN), usually requires high-performance supercomputers with dedicated accelerators, such as GPUs, FPGAs, or even Application-Specific Integrated Circuits (ASICs). Almost...
Autores principales: | Yang, Yu, Stathis, Dimitrios, Jordão, Rodolfo, Hemani, Ahmed, Lansner, Anders |
---|---|
Formato: | Online Artículo Texto |
Lenguaje: | English |
Publicado: |
Frontiers Media S.A.
2020
|
Materias: | |
Acceso en línea: | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC7487417/ https://www.ncbi.nlm.nih.gov/pubmed/32982673 http://dx.doi.org/10.3389/fnins.2020.00878 |
Ejemplares similares
-
Mapping the BCPNN Learning Rule to a Memristor Model
por: Wang, Deyu, et al.
Publicado: (2021) -
Reducing the computational footprint for real-time BCPNN learning
por: Vogginger, Bernhard, et al.
Publicado: (2015) -
Memory consolidation from seconds to weeks: a three-stage neural network model with autonomous reinstatement dynamics
por: Fiebig, Florian, et al.
Publicado: (2014) -
Learning to use working memory: a reinforcement learning gating model of rule acquisition in rats
por: Lloyd, Kevin, et al.
Publicado: (2012) -
Optimal Short-Sighted Rules
por: Bourgeois-Gironde, Sacha
Publicado: (2012)