4 papers
Plug-and-Play Spiking Operators: Breaking the Nonlinearity Bottleneck in Spiking Transformers
Xinzhe Yuan, Xiang Peng, Bin Gu +1
ANN-to-SNN conversion offers a practical, training-free route to spiking large language models. However, current pipelines primarily focus on spike-driven realizations for Transfor…
New Insight of Variance reduce in Zero-Order Hard-Thresholding: Mitigating Gradient Error and Expansivity Contradictions
Xinzhe Yuan, William de Vazelhes, Bin Gu +1
Hard-thresholding is an important type of algorithm in machine learning that is used to solve constrained optimization problems. However, the true gradient of the objectiv…
Temporal Misalignment in ANN-SNN Conversion and Its Mitigation via Probabilistic Spiking Neurons
Velibor Bojković, Xiaofeng Wu, Bin Gu
Spiking Neural Networks (SNNs) offer a more energy-efficient alternative to Artificial Neural Networks (ANNs) by mimicking biological neural principles, establishing them as a prom…
FTBC: Forward Temporal Bias Correction for Optimizing ANN-SNN Conversion
Xiaofeng Wu, Velibor Bojkovic, Bin Gu +2
Spiking Neural Networks (SNNs) offer a promising avenue for energy-efficient computing compared with Artificial Neural Networks (ANNs), closely mirroring biological neural processe…