Training Deep Architectures Without End-to-End Backpropagation: A Survey on the Provably Optimal Methods

Shiyu Duan, José C. Príncipe. Training Deep Architectures Without End-to-End Backpropagation: A Survey on the Provably Optimal Methods. IEEE Comp. Int. Mag., 17(4):39-51, 2022. [doi]

Abstract

Abstract is missing.