Oct, 2023
深度神经网络中的节点扰动有效学习
Effective Learning with Node Perturbation in Deep Neural Networks
Sander Dalm, Marcel van Gerven, Nasir Ahmad
TL;DRBackpropagation (BP) is the dominant method for training deep neural networks, but node perturbation (NP) proposes learning through noise injection and measurement of induced loss change, yielding competitive performance when aligned with directional derivatives and combining with a decorrelating mechanism for layer-wise inputs.