iScience · 2025 · Journal article
Evolutionary learning in neural networks by heterosynaptic plasticity
Combining evolutionary routing with dopamine-guided heterosynaptic plasticity trains biophysical spiking and analog neural networks without backpropagation.
The scientific question
How can complex biophysical neural networks learn effectively without gradient backpropagation?
Backpropagation struggles with instability and non-differentiable dynamics when optimizing detailed biophysical and spiking neuron models.

The core idea
Dopamine-Guided Evolutionary Heterosynaptic Plasticity
An evolutionary algorithm evaluates distinct neural routing pathways via alternating gating while guiding synaptic updates through dopamine modulation, dendritic meta-plasticity, and memory replay.
What we found
Gradient-Free Biophysical Network Training
The framework trains both feedforward and recurrent spiking or analog networks, reproducing cognitive-like neural dynamics and matching gradient-based performance on classification and control tasks.
Continue the question
Related reading
- Discovering heterogeneous synaptic plasticity rules via large-scale neural evolutionICLR 2026 · 2026
- Global Credit Assignment via Dynamical CriticalityICML 2026 · 2026
Cite this work
Zedong Bi, Ruiqi Fu, Guozhang Chen, Dongping Yang, Yu Zhou, Liang Tian. Evolutionary learning in neural networks by heterosynaptic plasticity. iScience, 2025. doi:10.1016/j.isci.2025.112340.