Synthetic Benchmarks Overstate Forward-Forward Scaling: Real-Data Limits of Layer-Local Training 事件

Synthetic Benchmarks Overstate Forward-Forward Scaling: Real-Data Limits of Layer-Local Training arXiv:2606.06539v1 Announce Type: new Abstract: Forward-Forward (FF) learning [Hinton, 2022] replaces backpropagation with strictly layer-local goodness updates. Recent FF-CNN work has narrowed the gap to BP on 32x32 benchmarks, raising the question of whether layer-local training is becoming a viable alternative at realistic scale. To probe this rigorously, we develop DTG-FF -- dynamic temperature