Heterogeneous Time Constants Improve Stability in Equilibrium Propagation
This work addresses a specific bottleneck in biologically plausible neural network training, offering an incremental improvement for researchers in computational neuroscience.
The paper tackled the issue of training stability in equilibrium propagation by introducing heterogeneous time steps based on biologically motivated distributions, resulting in improved stability while maintaining competitive task performance.
Equilibrium propagation (EP) is a biologically plausible alternative to backpropagation for training neural networks. However, existing EP models use a uniform scalar time step dt, which corresponds biologically to a membrane time constant that is heterogeneous across neurons. Here, we introduce heterogeneous time steps (HTS) for EP by assigning neuron-specific time constants drawn from biologically motivated distributions. We show that HTS improves training stability while maintaining competitive task performance. These results suggest that incorporating heterogeneous temporal dynamics enhances both the biological realism and robustness of equilibrium propagation.