canon-papers
collection · 2 published
canon-papers
AlexNet beat the last hand-built vision system by ten points
The paper measured every part it leaned on, which is why fourteen years on its survivors and its discards are still easy to name.
canon-papers
Adam's convergence proof was wrong and it still trains deep learning
Kingma and Ba built a nearly hyperparameter-free optimizer from two running averages of the gradient, then proved a convergence bound a simple convex problem would later break.