Cargando…
Event-Based Feature Extraction Using Adaptive Selection Thresholds
Unsupervised feature extraction algorithms form one of the most important building blocks in machine learning systems. These algorithms are often adapted to the event-based domain to perform online learning in neuromorphic hardware. However, not designed for the purpose, such algorithms typically re...
Autores principales: | Afshar, Saeed, Ralph, Nicholas, Xu, Ying, Tapson, Jonathan, van Schaik, André, Cohen, Gregory |
---|---|
Formato: | Online Artículo Texto |
Lenguaje: | English |
Publicado: |
MDPI
2020
|
Materias: | |
Acceso en línea: | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC7146588/ https://www.ncbi.nlm.nih.gov/pubmed/32183052 http://dx.doi.org/10.3390/s20061600 |
Ejemplares similares
-
Investigation of Event-Based Surfaces for High-Speed Detection, Unsupervised Feature Extraction, and Object Recognition
por: Afshar, Saeed, et al.
Publicado: (2019) -
Real-Time Event-Based Unsupervised Feature Consolidation and Tracking for Space Situational Awareness
por: Ralph, Nicholas, et al.
Publicado: (2022) -
Event-driven spectrotemporal feature extraction and classification using a silicon cochlea model
por: Xu, Ying, et al.
Publicado: (2023) -
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)