Receptive Field
/rɪˈsɛptɪv fiːld/
The region of input space that affects a particular neuron's activation in a neural network.
In italiano: Receptive FieldIn CNNs, receptive field grows with each layer. Deeper neurons see larger input regions. Determined by filter size, stride, and network depth. Critical for understanding what information neurons can access.
Examples
- 3x3 filter has 3x3 receptive field
- Deeper layers see larger regions
- Dilated convolutions increase receptive field