Reference 3 stops to get here
Padding
Adding borders of zeros (or other values) around input to control output spatial dimensions in convolutions.
Your route here
3 stops · basics first
- Machine Learning ✓ understood
Building systems that learn patterns from data instead of following hand-written rules, getting better at a task as they see more examples.
- Neural Network ✓ understood
A model built from layers of simple units, each taking a weighted sum of its inputs and applying a nonlinearity; training adjusts the weights so the whole stack maps inputs to useful outputs.
- Convolution ✓ understood
A mathematical operation that applies filters/kernels to input data to extract features like edges, textures, and patterns.
- Padding · you are here ✓ understood
Where it sits
Explore nearby
Neural Networks Stride The step size by which a convolutional filter or pooling window moves across the input. Neural Networks Kernel A small matrix of weights used in convolutional layers to detect specific features or patterns in input data. Neural Networks Feature Map The output of applying a convolutional filter to an input, representing detected features at various spatial locations. Neural Networks Receptive Field The region of input that influences a particular neuron's output, growing larger in deeper layers of CNNs.