computer-vision
Convolution as a learned operation, pooling, and receptive fields
taught
Distinguishing a CNN's learned kernel (weights set by training) from a fixed hand-designed kernel (Sobel, Gaussian), and tracking how pooling and stacked layers grow a unit's receptive field while shrinking the parameter count relative to a fully connected layer.
Taught in
Requires
-
multichannel-convolution
recommended
deep-learning ch.15 derives multi-channel and 1x1 convolution mechanics in full; this course's own quizzes only require the working-depth version taught locally.
Required by
Nothing in the catalog needs this yet.
Local knowledge map
Local knowledge map
Click to expand
Solid arrows are required prerequisites; dashed are recommended or helpful. Lower rows are more foundational. Click any box to jump to that concept.