Sakana AI's PC-ALM Trains 1,000-Layer Networks Without Backpropagation
This story is from 2026-09-14. It is preserved in the archive; the latest stories are on the live feed.
Sakana AI's PC-ALM adds Lagrange multipliers to predictive coding, training 1000-layer networks with only layer-local dynamics and no backpropagation.
Read the full story at AlphaSignal ↗
Timeline · 1 report
- 2026-09-14 12:00 · AlphaSignal
Sakana AI's PC-ALM Trains 1,000-Layer Networks Without Backpropagation