Learning Internal Biological Neuron Parameters and Complexity-Based Encoding for Improved Spiking Neural Networks Performance

TL;DR

This paper introduces a biologically grounded learning paradigm for spiking neural networks that jointly optimizes synaptic and intrinsic neuronal parameters, improving classification accuracy and interpretability with theoretical guarantees.

Contribution

It proposes a novel learning framework that optimizes intrinsic neuron parameters in SNNs, enhancing performance and interpretability over traditional methods.

Findings

Intrinsic parameter learning improves accuracy by up to 13.5%.

The SNN-LZC classifier achieves 99.5% accuracy with low latency.

Theoretical analysis links intrinsic optimization to hypothesis class expansion.

Abstract

This study proposes a novel learning paradigm for spiking neural networks (SNNs) that replaces the perceptron-inspired abstraction with biologically grounded neuron models, jointly optimizing synaptic weights and intrinsic neuronal parameters. We evaluate two architectures, leaky integrate-and-fire (LIF) and a meta-neuron model, under fixed and learnable intrinsic dynamics. Additionally, we introduce a biologically inspired classification framework that combines SNN dynamics with Lempel-Ziv complexity (LZC), enabling efficient and interpretable classification of spatiotemporal spike data. Training is conducted using surrogate-gradient backpropagation, spike-timing-dependent plasticity (STDP), and the Tempotron rule on spike trains generated from Poisson processes, widely adopted in computational neuroscience as a standard stochastic model of neuronal spike generation due to their analytical tractability and empirical relevance. Learning intrinsic parameters improves classification accuracy by up to 13.50 percentage points for LIF networks and 8.50 for meta-neuron models compared to baselines tuning only network size and learning rate. The proposed SNN-LZC classifier achieves up to 99.50% accuracy with sub-millisecond inference latency and competitive energy consumption. We further provide theoretical justification by formalizing how optimizing intrinsic dynamics enlarges the hypothesis class and proving descent guarantees for intrinsic-parameter updates under standard smoothness assumptions, linking intrinsic optimization to provable improvements in the surrogate objective.