Augmented Lagrangian Predictive Coding: training 1000-layer networks without backpropagation
pub.sakana.ai · saved by 1 readers
A local alternative to backpropagation. PC-ALM trains residual MLPs up to 1000 layers, nearly matching backprop's performance despite using only layer-local dynamics. PC-ALM equips each layer with a feedback control dynamical system that distributes and propagates supervision credit throughout a network.