Cargando…
Fast Convergence of Competitive Spiking Neural Networks with Sample-Based Weight Initialization
Recent work on spiking neural networks showed good progress towards unsupervised feature learning. In particular, networks called Competitive Spiking Neural Networks (CSNN) achieve reasonable accuracy in classification tasks. However, two major disadvantages limit their practical applications: high...
Autores principales: | Cachi, Paolo Gabriel, Ventura, Sebastián, Cios, Krzysztof Jozef |
---|---|
Formato: | Online Artículo Texto |
Lenguaje: | English |
Publicado: |
2020
|
Materias: | |
Acceso en línea: | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC7274752/ http://dx.doi.org/10.1007/978-3-030-50153-2_57 |
Ejemplares similares
-
CRBA: A Competitive Rate-Based Algorithm Based on Competitive Spiking Neural Networks
por: Cachi, Paolo G., et al.
Publicado: (2021) -
Quantization Framework for Fast Spiking Neural Networks
por: Li, Chen, et al.
Publicado: (2022) -
Synaptic convergence regulates synchronization-dependent spike transfer in feedforward neural networks
por: Sailamul, Pachaya, et al.
Publicado: (2017) -
Competitive Learning in a Spiking Neural Network: Towards an Intelligent Pattern Classifier
por: Lobov, Sergey A., et al.
Publicado: (2020) -
Recurrent Spiking Neural Network Learning Based on a Competitive Maximization of Neuronal Activity
por: Demin, Vyacheslav, et al.
Publicado: (2018)