论文标题
长期的短期内存尖峰网络及其应用
Long Short-Term Memory Spiking Networks and Their Applications
论文作者
论文摘要
基于事件的神经形态系统的最新进展引起了人们对尖峰神经网络（SNN）的使用和发展的重大兴趣。但是，峰值神经元的非差异性质使SNN与常规的反向传播技术不相容。尽管在训练常规深度神经网络（DNN）方面取得了重大进展，但SNN的培训方法仍然相对较差。在本文中，我们提出了一个新颖的培训训练循环SNN的框架。类似于DNN中学习时间序列模型中经常性神经网络（RNN）所带来的好处，我们基于长期记忆（LSTM）网络开发SNN。我们表明，LSTM尖峰网络学习了峰值和时间依赖性的时间。我们还开发了一种基于LSTM的SNN中错误反向传播的方法。基于LSTM的SNN中为反向传播的已开发的架构和方法使他们能够学习与常规LSTMS相当结果的长期依赖性。
Recent advances in event-based neuromorphic systems have resulted in significant interest in the use and development of spiking neural networks (SNNs). However, the non-differentiable nature of spiking neurons makes SNNs incompatible with conventional backpropagation techniques. In spite of the significant progress made in training conventional deep neural networks (DNNs), training methods for SNNs still remain relatively poorly understood. In this paper, we present a novel framework for training recurrent SNNs. Analogous to the benefits presented by recurrent neural networks (RNNs) in learning time series models within DNNs, we develop SNNs based on long short-term memory (LSTM) networks. We show that LSTM spiking networks learn the timing of the spikes and temporal dependencies. We also develop a methodology for error backpropagation within LSTM-based SNNs. The developed architecture and method for backpropagation within LSTM-based SNNs enable them to learn long-term dependencies with comparable results to conventional LSTMs.
