Deep learning
Posts with this tag
Posts
-
Convolutions, Receptive Fields, and Why Stacked 3×3 Kernels Work
A NumPy conv2d, the arithmetic of receptive-field growth, an edge-detection example on a synthetic image, and the parameter count that explains why modern CNNs use small kernels.
-
Backpropagation by Hand: A Two-Layer MLP in NumPy with a Gradient Check
Deriving every gradient of a small multilayer perceptron, implementing it in NumPy, and proving the implementation right with a finite-difference check before training it.
