This study revisits SNN robustness through the lens of temporal granularity, emphasizing the distinct behaviors that occur at individual time steps and proposes a Temporal Granularity Regu-larization term that constrains the TSV across all time steps, thereby improving the model’s overall robustness.
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.
Yajie Zhai, Yanmei Kang, Meng Li et al.· 0 citations
Spiking neural networks (SNNs) promise energyefficient temporal processing, but the choice of neuron model affects both task accuracy and hardware cost. We compare three mechanisms for enriching temporal processing in SNNs- heterogeneity, adaptation, and synaptic delays-on auditory benchmarks (SHD, SSC) under controlle...
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 correlatio...
Rong Xiao, Zhi-Yuan Hu, Ping He et al.· IEEE Transactions on Image P...· 0 citations
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...
N. T. Luu, Trung Duong Trung Luu, N. Pham et al.· Neuromorphic Computing and E...· 0 citations
With the development of neuromorphic computing, threshold-switching devices have been widely explored for implementing artificial neurons, but the stability of such circuits remains a critical challenge. This work systematically investigates the Hodgkin–Huxley (HH) neuron based on NbOx threshold devices from the perspe...
Hui-Ling Chen, Hao-Ran Chen, Qing-Hai Xia et al.· Journal of Applied Physics· 0 citations
This work reformulates temporal credit assignment as a state separation problem: extracting task-required components induced by historical perturbations directly from the current neural state, which enables an online feedback learning framework for NMCs through a gradient tunneling algorithm and the lead-lag expansion...
Xiang-Nan Zhang, Jing-Xin Liu, Ran-Qi Lu et al.· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
