Robust Spiking Neural Networks by Temporal Mutual Information

On the Role of Temporal Granularity in the Robustness of Spiking Neural Networks

Noisy group neurons with synchronous resetting for high-performance spiking neural networks

This work proposes a noisy group neuron (NGN) model, which incorporates population-level synchronous resetting and neural stochasticity as fundamental computational mechanisms, and develops the NGN method as a framework that combines the NGN model with backpropagation learning based on mean-field dynamics.

Why temporal spike order reversal drops spiking network accuracy and how to partially mitigate it

This study identifies a critical vulnerability in SNNs on recently established bit-based codes: consistent performance degradation when temporal spike encoding orders are reversed, and measures the per-timestep class-mutual-information profile of six encodings directly and shows that the resulting concordance ordering predicts the observed degradation.

OT-SAN: One Timestep Spiking Actor Network With Mask-Adaptive Global Connection and Dynamic Thresholds

Spiking neural networks (SNNs) have garnered significant attention in reinforcement learning tasks for their low power consumption. However, traditional spiking reinforcement learning (SRL) methods, which rely on local-connected encoding and fixed-threshold learning, struggle to capture the inter-dimensional correlations of input information within short timesteps, limiting the network’s expressive capacity at low timesteps. While increasing timesteps can significantly enhance performance, excessive timesteps result in substantial delays. To address this contradiction and enhance the expressive and decision-making capabilities of SNNs within short timesteps, we propose Mask-Adaptive Global Connection (MAGC), a novel encoding method that efficiently captures long-range dependencies via sparse, adaptively masked connections—enabling global feature interaction in a single timestep. Additionally, dynamic-threshold spiking neurons are introduced to effectively capture and distinguish subtle changes in input signals at each timestep, thereby enhancing the spatial-temporal state representation during spike information transmission. Extensive experimental results demonstrate that the proposed method achieves performance comparable to state-of-the-art algorithms using only a single timestep, while significantly reducing inference latency and energy consumption. When extended to multiple timesteps, our approach consistently outperforms existing methods, showing substantial improvements across eight continuous control tasks from OpenAI Gym.

Stable and compute-resource efficient learning with spiking and quantum neural networks

This thesis investigates stable learning and compute-resource efficiency on spiking neural networks and hybrid classical-quantum neural networks, which have become more complex architectures such as spiking neural networks and quantum neural networks.

PMSN: A Parallel Multi-Compartment Spiking Neuron for Multiscale Temporal Processing.

The proposed parallel multi-compartment spiking neuron (PMSN) presents a promising solution to harness the computational advantages of detailed biological neurons, enabling high-performance and efficient temporal processing on neuromorphic computing systems.