News for hackers. Stuff that matters.

A comment on Backprop Alternative: Augmented Lagrangian Predictive Coding. Parent comment

Re:Backprop Alternative: Augmented Lagrangian Predictive Coding by bz_bz_bz on Monday September 14, 2026 @06:13PM (#49704922)
Their image classification benchmarks include both: https://pub.sakana.ai/pc-alm/assets/figures/benchmark_accura...
[ Parent | on HN ]
Re:Backprop Alternative: Augmented Lagrangian Predictive Coding by cs702 on Monday September 14, 2026 @07:32PM (#49705692)
~74% on CIFAR-10. Still a far cry from backprop.

I didn't see ImageNet. TinyImageNet is something else.

[ Parent | on HN ]
Re:Backprop Alternative: Augmented Lagrangian Predictive Coding by rocketships on Tuesday September 15, 2026 @04:57AM (#49709684)
There might be only one paper that's trained on full Imagenet using methods like these.

Training a Predictive Coding Network on ImageNet using Equilibrium Propagation Tugdual Kerjan, Rasmus Høier, Benjamin Scellier https://arxiv.org/abs/2606.03584

It's quite an undertaking.

[ Parent | on HN ]