Error Broadcast and Decorrelation as a Potential Artificial and Natural Learning Mechanism
NeurIPSSpotlight2025
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