Toward Efficient Processing and Learning With Spikes: New Approaches for Multispike Learning
Toward Efficient Processing and Learning With Spikes: New Approaches for Multispike Learning
复制标题
利用尖峰实现高效处理和学习：多尖峰学习的新方法
DOI：
10.1109/tcyb.2020.2984888
复制
发表时间：
2020-04
影响因子：
11.8
通讯作者：
Kay Chen Tan
中科院分区：
文献类型：
--
作者：
Qiang Yu;Shenglan Li;Huajin Tang;Longbiao Wang;Jianwu Dang;Kay Chen Tan
尖峰是中枢神经系统中用于信息传输和处理的货币。它们也被认为在生物系统的低功耗中起着至关重要的作用，其效率越来越受到神经形态计算领域的关注。然而，离散尖峰的有效处理和学习仍然是一个具有挑战性的问题。在本文中，我们将朝着这个方向做出自己的贡献。首先介绍了一个简化的发放神经元模型，其中突触输入和发放输出对膜电位的影响用脉冲函数来建模。为了进一步提高处理效率，提出了一种事件驱动的方案。基于神经元模型，我们提出了两个新的多尖峰学习规则，这些规则在各种任务（包括关联、分类和特征检测）上表现出比其他基线更好的性能。除了效率，我们的学习规则表现出对不同类型的强噪声的高鲁棒性。它们也可以推广到不同的尖峰编码方案的分类任务，值得注意的是，单个神经元能够解决多类别分类与我们的学习规则。在特征检测任务中，我们重新审视了无监督尖峰时间依赖可塑性的能力，并提出了其局限性，并发现了一个新的现象，失去选择性。相比之下，我们提出的学习规则可以在广泛的条件下可靠地解决任务，而无需应用特定的约束。此外，我们的规则不仅可以检测功能，但也区分他们。我们的方法的改进性能将有助于神经形态计算作为一个更好的选择。
Spikes are the currency in central nervous systems for information transmission and processing. They are also believed to play an essential role in low-power consumption of the biological systems, whose efficiency attracts increasing attentions to the field of neuromorphic computing. However, efficient processing and learning of discrete spikes still remain a challenging problem. In this article, we make our contributions toward this direction. A simplified spiking neuron model is first introduced with the effects of both synaptic input and firing output on the membrane potential being modeled with an impulse function. An event-driven scheme is then presented to further improve the processing efficiency. Based on the neuron model, we propose two new multispike learning rules which demonstrate better performance over other baselines on various tasks, including association, classification, and feature detection. In addition to efficiency, our learning rules demonstrate high robustness against the strong noise of different types. They can also be generalized to different spike coding schemes for the classification task, and notably, the single neuron is capable of solving multicategory classifications with our learning rules. In the feature detection task, we re-examine the ability of unsupervised spike-timing-dependent plasticity with its limitations being presented, and find a new phenomenon of losing selectivity. In contrast, our proposed learning rules can reliably solve the task over a wide range of conditions without specific constraints being applied. Moreover, our rules cannot only detect features but also discriminate them. The improved performance of our methods would contribute to neuromorphic computing as a preferable choice.
登录
查看更多内容
影响因子：
25
作者：
Song, S;Miller, KD;Abbott, LF
通讯作者：
Abbott, LF
DOI：
10.1007/springerreference_32706
发表时间：
2020-11
期刊：
Neuromuscular Fundamentals
影响因子：
--
作者：
N. H. Sabah
通讯作者：
N. H. Sabah
影响因子：
4.3
作者：
Nessler B;Pfeiffer M;Buesing L;Maass W
通讯作者：
Maass W
DOI：
10.1080/2153599x.2014.951911
发表时间：
2014-09
期刊：
Religion, Brain & Behavior
影响因子：
--
作者：
W. Wildman;R. Sosis;P. McNamara
通讯作者：
W. Wildman;R. Sosis;P. McNamara
影响因子：
64.8
作者：
HOPFIELD, JJ
通讯作者：
HOPFIELD, JJ