arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2005.11633cs.NEcs.LG
收藏

多时间尺度脉冲循环神经网络的高效计算

Effective and Efficient Computation with Multiple-timescale Spiking Recurrent Neural Networks

CWI(荷兰国家数学与计算机科学研究所);IMEC(比利时微电子研究中心)

Bojian Yin, Federico Corradi, Sander M. Bohté

摘要:

受大脑启发的类脑计算作为边缘AI的范例的出现,正在激励人们寻找在这种硬件上运行的高性能和高效的脉冲神经网络。然而,与深度学习中的经典神经网络相比,当前的脉冲神经网络在引人注目的领域缺乏竞争力。在这里,对于顺序和流式任务,我们演示了一种新型的自适应尖峰递归神经网络(SRNN)与其他脉冲神经网络相比,如何能够实现最先进的性能,并且几乎达到或超过经典循环神经网络(RNN)的性能,同时表现出稀疏的活动。由此,我们计算出SRNN在更困难的任务上比经典RNN的能量提高了$>$ 100倍。为了实现这一目标,我们将标准和自适应多时间尺度尖峰神经元建模为自循环神经单元,并利用PyTorch深度学习框架中的代理梯度和自动微分来有效地实现时间反向传播,包括学习重要的尖峰神经元参数,以使我们的尖峰神经元适应任务。

英文摘要:

The emergence of brain-inspired neuromorphic computing as a paradigm for edge AI is motivating the search for high-performance and efficient spiking neural networks to run on this hardware. However, compared to classical neural networks in deep learning, current spiking neural networks lack competitive performance in compelling areas. Here, for sequential and streaming tasks, we demonstrate how a novel type of adaptive spiking recurrent neural network (SRNN) is able to achieve state-of-the-art performance compared to other spiking neural networks and almost reach or exceed the performance of classical recurrent neural networks (RNNs) while exhibiting sparse activity. From this, we calculate a $>$100x energy improvement for our SRNNs over classical RNNs on the harder tasks. To achieve this, we model standard and adaptive multiple-timescale spiking neurons as self-recurrent neural units, and leverage surrogate gradients and auto-differentiation in the PyTorch Deep Learning framework to efficiently implement backpropagation-through-time, including learning of the important spiking neuron parameters to adapt our spiking neurons to the tasks.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑