Spiking Neural Networks (SNNs) are highly energy-efficient due to event-driven, sparse computation, but their training is challenged by spike non-differentiability and trade-offs among performance, efficiency, and biological plausibility. Crucially, mainstream SNNs ignore predictive coding, a core cortical mechanism where the brain predicts inputs and encodes errors for efficient perception. Inspired by this, we propose a self-prediction enhanced spiking neuron method that generates an internal prediction current from its input-output history to modulate membrane potential. This design offers dual advantages, it creates a continuous gradient path that alleviates vanishing gradients and boosts training stability and accuracy, while also aligning with biological principles, which resembles distal dendritic modulation and error-driven synaptic plasticity. Experiments show consistent performance gains across diverse architectures, neuron types, time steps, and tasks demonstrating broad applicability for enhancing SNNs.
@article{arxiv.2601.21823,
title = {General Self-Prediction Enhancement for Spiking Neurons},
author = {Zihan Huang and Zijie Xu and Yihan Huang and Shanshan Jia and Tong Bu and Yiting Dong and Wenxuan Liu and Jianhao Ding and Zhaofei Yu and Tiejun Huang},
journal= {arXiv preprint arXiv:2601.21823},
year = {2026}
}