Evolutionary learning in neural networks by heterosynaptic plasticity
Zedong Bi, Ruiqi Fu, Guozhang Chen, Dongping Yang, Yu Zhou, Liang Tian · iScience · 2025
Training biophysical neuron models provides insights into brain circuits’ organization and problem-solving capabilities. Traditional training methods like backpropagation face challenges with complex models due to instability and gradient issues. We explore evolutionary algorithms (EAs) combined with heterosynaptic plasticity as a gradient-free alternative. Our EA models agents with distinct neuron information routes, evaluated via alternating gating, and guided by dopamine-driven plasticity. This model draws inspiration from various biological mechanisms, such as dopamine function, dendritic spine meta-plasticity, memory replay, and cooperative synaptic plasticity within dendritic neighborhoods. Neural networks trained with this model recapitulate brain-like dynamics during cognition. Our method effectively trains spiking and analog neural networks in both feedforward and recurrent architectures, it also achieves performance in tasks like MNIST classification and Atari games comparable to gradient-based methods. Overall, this research extends training approaches for biophysical neuron models, offering a robust alternative to traditional algorithms. • Evolutionary algorithms (EAs) offer a gradient-free alternative to backpropagation • EA model draws inspiration from various biological mechanisms • Heterosynaptic plasticity aids network training through the EA model • EA model trains versatile networks, matching brain-like dynamics, and top-tier performance Biological sciences; Neuroscience; Biophysics