论文标题
BISNN：通过贝叶斯学习训练具有二元重量的培训神经网络
BiSNN: Training Spiking Neural Networks with Binary Weights via Bayesian Learning
论文作者
论文摘要
通过限制突触权重为二进制，可以使基于人工神经网络（ANN）对电池供电的设备的推断更加节能，从而消除了执行乘法的需求。另一种新兴方法依赖于使用尖峰神经网络（SNNS），生物学启发，动态，事件驱动的模型，这些模型通过使用二进制，稀疏，激活来提高能源效率。在本文中，引入了SNN模型，该模型结合了暂时稀疏的二元激活和二进制重量的好处。得出了两个学习规则，这是基于直通梯度技术的组合，而第二个基于贝叶斯范式的组合。实验验证了有关全精度实现的性能损失，并在准确性和校准方面证明了贝叶斯范式的优势。
Artificial Neural Network (ANN)-based inference on battery-powered devices can be made more energy-efficient by restricting the synaptic weights to be binary, hence eliminating the need to perform multiplications. An alternative, emerging, approach relies on the use of Spiking Neural Networks (SNNs), biologically inspired, dynamic, event-driven models that enhance energy efficiency via the use of binary, sparse, activations. In this paper, an SNN model is introduced that combines the benefits of temporally sparse binary activations and of binary weights. Two learning rules are derived, the first based on the combination of straight-through and surrogate gradient techniques, and the second based on a Bayesian paradigm. Experiments validate the performance loss with respect to full-precision implementations, and demonstrate the advantage of the Bayesian paradigm in terms of accuracy and calibration.
