Cargando…
Investigation of Event-Based Surfaces for High-Speed Detection, Unsupervised Feature Extraction, and Object Recognition
In this work, we investigate event-based feature extraction through a rigorous framework of testing. We test a hardware efficient variant of Spike Timing Dependent Plasticity (STDP) on a range of spatio-temporal kernels with different surface decaying methods, decay functions, receptive field sizes,...
Autores principales: | Afshar, Saeed, Hamilton, Tara Julia, Tapson, Jonathan, van Schaik, André, Cohen, Gregory |
---|---|
Formato: | Online Artículo Texto |
Lenguaje: | English |
Publicado: |
Frontiers Media S.A.
2019
|
Materias: | |
Acceso en línea: | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC6344467/ https://www.ncbi.nlm.nih.gov/pubmed/30705618 http://dx.doi.org/10.3389/fnins.2018.01047 |
Ejemplares similares
-
Event-Based Feature Extraction Using Adaptive Selection Thresholds
por: Afshar, Saeed, et al.
Publicado: (2020) -
Real-Time Event-Based Unsupervised Feature Consolidation and Tracking for Space Situational Awareness
por: Ralph, Nicholas, et al.
Publicado: (2022) -
Synthesis of neural networks for spatio-temporal spike pattern recognition and processing
por: Tapson, Jonathan C., et al.
Publicado: (2013) -
Racing to learn: statistical inference and learning in a single spiking neuron with adaptive kernels
por: Afshar, Saeed, et al.
Publicado: (2014) -
The ripple pond: enabling spiking networks to see
por: Afshar, Saeed, et al.
Publicado: (2013)