AI RESEARCH
Covariance-Aware Goodness for Scalable Forward-Forward Learning
arXiv CS.LG
•
ArXi:2605.04346v1 Announce Type: new The Forward-Forward algorithm eliminates global gradient flow and full network activations storage. However, in convolutional settings, existing BP-free FF methods significantly under-perform backpropagation on complex benchmarks such as ImageNet-100 and Tiny-ImageNet. We identify this gap as a structural bottleneck in goodness extraction: standard sum-of-squares formulation collapses feature volumes into channel-wise activation energies which omits critical second-order dependencies.