login sign up

Augmented Lagrangian Predictive Coding: training 1000-layer networks without backpropagation

pub.sakana.ai · first added by @kmurph
saved by
1 person
related read on
Dust: Pretraining Transformers Without Backpropagation from the discussion
discussions · 1
Backprop Alternative: Augmented Lagrangian Predictive Coding 128 pts · 45 comments · Sep 2026 128 pts · 45 comments · Sep 2026
0 people saved or upvoted this
from the discussion · 3
https://direct.mit.edu/neco/article/34/6/1329/110646/Predictive-Coding-Approximates-Backprop-Along direct.mit.edu direct.mit.edu
0 people saved or upvoted this
Training a Predictive Coding Network on ImageNet using Equilibrium Propagation arxiv.org arxiv.org
0 people saved or upvoted this
Augmented Lagrangian Predictive Coding arxiv.org arxiv.org
0 people saved or upvoted this