Error Broadcast and Decorrelation as a Potential Artificial and Natural Learning Mechanism

NeurIPSSpotlight2025

Authors
Mete Erdogan, Cengiz Pehlevan, Alper Tunga Erdogan
Venue
NeurIPS 2025
Track
Spotlight

TL;DR

We introduce *Error Broadcast and Decorrelation* (EBD), a novel learning framework for neural networks that addresses credit assignment by directly broadcasting output errors to individual layers, cir…

Opening excerpt from the authors’ abstract. source

Read the paper

← All NeurIPS 2025 Spotlight papers · Browse the whole archive