Artificial Intelligence / AI 0537 · Atom · ~20 seconds
Weight Sharing
Video not yet published
to the StudyWalks catalog
to the StudyWalks catalog
State
A convolutional layer uses the same template weights at every position — a pattern learned anywhere is recognized everywhere, and the knob count collapses to template-sized.
Show
The corner cat and the centered cat finally meet the same detectors; the overfitting appetite drops to a feedable size.
Watch for
Weight sharing made deep seeing learnable at all — the one big trick, not an optimization detail.