论文标题
EQSPIKE：神经形态实现的尖峰驱动的平衡传播
EqSpike: Spike-driven Equilibrium Propagation for Neuromorphic Implementations
论文作者
论文摘要
在神经形态系统的局部约束中，找到基于尖峰的学习算法，同时达到高精度，这仍然是一个巨大的挑战。平衡传播是反向传播的有希望的替代方法，因为它仅涉及本地计算，但是以硬件为导向的研究迄今已集中在基于费率的网络上。在这项工作中，我们开发了一种称为eqspike的尖峰神经网络算法，与神经形态系统兼容，该系统通过平衡传播学习。通过模拟，我们获得了MNIST的测试识别精度为97.6％，类似于基于速率的平衡传播，并与尖峰神经网络的替代学习技术进行了比较。我们表明，与GPU相比，在硅神经形态技术中实施的EQSPIKE可以分别通过三个顺序和两个数量级来分别减少推理和训练的能源消耗。最后，我们还表明，在学习过程中，EQSPIKE重量更新表现出一种峰值定时依赖性可塑性的形式，突出了可能与生物学的联系。
Finding spike-based learning algorithms that can be implemented within the local constraints of neuromorphic systems, while achieving high accuracy, remains a formidable challenge. Equilibrium Propagation is a promising alternative to backpropagation as it only involves local computations, but hardware-oriented studies have so far focused on rate-based networks. In this work, we develop a spiking neural network algorithm called EqSpike, compatible with neuromorphic systems, which learns by Equilibrium Propagation. Through simulations, we obtain a test recognition accuracy of 97.6% on MNIST, similar to rate-based Equilibrium Propagation, and comparing favourably to alternative learning techniques for spiking neural networks. We show that EqSpike implemented in silicon neuromorphic technology could reduce the energy consumption of inference and training respectively by three orders and two orders of magnitude compared to GPUs. Finally, we also show that during learning, EqSpike weight updates exhibit a form of Spike Timing Dependent Plasticity, highlighting a possible connection with biology.
