Neuronal Self-Adaptation Enhances Capacity and Robustness of Representation in Spiking Neural Networks

2026-03-21

AI Summary

This work addresses the limited information capacity and noise sensitivity of traditional leaky integrate-and-fire (LIF) neuron models, which constrain the accuracy and robustness of spiking neural networks. Inspired by the self-regulatory mechanisms of biological potassium channels, we propose a potassium-gated LIF (KvLIF) neuron model that, for the first time, integrates biologically plausible plasticity into the LIF framework. By introducing an auxiliary conductance state that fuses membrane potential with spike history, KvLIF adaptively modulates neuronal excitability and reset dynamics. This mechanism effectively broadens the dynamic response range, suppresses noise, and substantially enhances representational capacity. Evaluated across multiple static and neuromorphic datasets, KvLIF achieves higher classification accuracy and greater noise robustness while retaining the potential for low-power deployment.

Technology Category

• Cognitive Modeling & Cognitive Systems: Neural Spike Coding
• Machine Learning: Bio-inspired Learning
• Natural Language Processing: Learning & Optimization for NLP

Application Category

• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Search and Retrieval-Augmented AI: Large language models for search
• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs

Abstract

Spiking Neural Networks (SNNs) are promising for energy-efficient, real-time edge computing, yet their performance is often constrained by the limited adaptability of conventional leaky integrate-and-fire (LIF) neurons. Existing LIF models struggle with restricted information capacity and susceptibility to noise, leading to degraded accuracy and compromised robustness. Inspired by the dynamic self-regulation of biological potassium channels, we propose the Potassium-regulated LIF (KvLIF) neuron model. KvLIF introduces an auxiliary conductance state that integrates membrane potential and spiking history to adaptively modulate neuronal excitability and reset dynamics. This design extends the dynamic response range of neurons to varying input intensities and effectively suppresses noise-induced spikes. We extensively evaluate KvLIF on both static image and neuromorphic datasets, demonstrating consistent improvements in classification accuracy and superior robustness compared to existing LIF models. Our work bridges biological plausibility with computational efficiency, offering a neuron model that enhances SNN performance while maintaining suitability for low-power neuromorphic deployment.

Problem

• Spiking Neural Networks
• Leaky Integrate-and-Fire
• Neuronal Adaptability
• Information Capacity
• Robustness

Innovation

• Spiking Neural Networks
• KvLIF neuron
• self-adaptation
• noise robustness
• neuromorphic computing