DEQ
Deep Equilibrium Models
2000년 도입 · 논문 42편에서 사용
A new kind of implicit models, where the output of the network is defined as the solution to an "infinite-level" fixed point equation. Thanks to this we can compute the gradient of the output without activations and therefore with a significantly reduced memory footprint.
소개 논문: Deep Equilibrium Models
Robust Training · General