Filter / Kernel
/ˈfɪltər ˈkɜːrnəl/
Filter / Kernel: A small matrix of learnable weights that slides over input during convolution to detect specific features. Filters are learned during training to detect useful features. Common sizes: 3x3, 5x5, 7x7. Multiple filters extract different features. The term 'kernel' is used interchangeably with filter.
In italiano: Filtro / KernelLegge I · Embedding, feature e spazi vettorialiFilters are learned during training to detect useful features. Common sizes: 3x3, 5x5, 7x7. Multiple filters extract different features. The term 'kernel' is used interchangeably with filter.
Examples
- 3x3 edge detection filter
- 5x5 Gaussian blur kernel
- Learned feature detectors
Autovalutazione
Tre domande per verificare la comprensione della voce. Le spiegazioni restano disponibili anche senza JavaScript.