AI RESEARCH
Dendritic Neural Networks with Equilibrium Propagation
arXiv CS.LG
•
ArXi:2605.08135v1 Announce Type: new Equilibrium propagation (EP) is a biologically plausible alternative to backpropagation (BP), but its effectiveness can degrade in deeper and challenging learning settings. In parallel, dendritic neural networks have nstrated improved performance and generalization when trained with BP, suggesting that structured, biologically inspired architectures may enhance learning. In this work, we investigate the integration of dendritic neural networks with equilibrium propagation using an advanced EP framework.