The maximum points-based supervised learning rule for spiking neural networks
The maximum points-based supervised learning rule for spiking neural networks
复制标题
尖峰神经网络基于最大点的监督学习规则
DOI：
10.1007/s00500-018-3576-0
复制
发表时间：
2018-11
期刊：
影响因子：
4.1
通讯作者：
Zhang Malu
中科院分区：
文献类型：
--
作者：
Xie Xiurui;Liu Guisong;Cai Qing;Qu Hong;Zhang Malu
作为第三代神经网络，尖峰神经网络（SNN）在模式识别领域取得了巨大成功。然而，由于时间编码机制，现有的 SNN 训练方法不够有效。为了提高监督SNN的训练效率并保留有用的时间信息，本文提出了基于最大点的监督学习规则（MPSLR）。 MPSLR 采用三种训练策略来提高学习性能。首先，仅训练目标点和最大电压点。通过理论分析，我们发现最大点对于非目标点的电压控制是有效的，并且所有最大电压点的解析解都是可以并行获得的。通过避免连续的电压检测，显着提高了训练效率。其次，通过速率函数对每个突触前神经元的权重修改进行标准化，以调整输出规模。第三，利用在一个时间窗口内累积的尖峰率来获取更多有用的知识。对合成数据和四个真实 UCI 数据集的大量实验表明，我们的算法在各种情况下（包括不同的多尖峰率和时间长度）比传统方法取得了显着更好的性能和更高的效率。此外，它对超参数变化更加稳定。
As the third generation of neural networks, Spiking Neural Networks (SNNs) have made great success in pattern recognition fields. However, the existing training methods for SNNs are not efficient enough because of the temporal encoding mechanism. To improve the training efficiency of the supervised SNNs and keep the useful temporal information, the Maximum Points-based Supervised Learning Rule (MPSLR) is proposed in this paper. Three training strategies are adopted in MPSLR to improve the learning performance. Firstly, only the target points and maximum voltage points are trained. By theoretical analyses, we find that the maximum points are effective for the voltage controlling of the non-target points, and the analytic solutions for all maximum voltage points are parallelly obtainable. This improves the training efficiency significantly by avoiding the successive voltage detecting. Secondly, the weight modification for each presynaptic neuron is normalized by a rate function to resizing the output scale. Thirdly, the spiking rates accumulated in a time window are utilized to involve more useful knowledge. Extensive experiments on both synthetic data and four real-world UCI datasets demonstrate that our algorithm achieves significantly better performance and higher efficiency than traditional methods in various situations, including different multi-spike rates and time lengths. Besides, it is more stable to hyper-parameter variations.
登录
查看更多内容
DOI：
10.1109/csit.2016.7549453
发表时间：
2016-07
期刊：
2016 7th International Conference on Computer Science and Information Technology (CSIT)
影响因子：
--
作者：
L. Abualigah;A. Khader;M. Al-Betar
通讯作者：
L. Abualigah;A. Khader;M. Al-Betar
影响因子：
2.9
作者：
Yan Xu;Xiaoqin Zeng;Shuiming Zhong
通讯作者：
Yan Xu;Xiaoqin Zeng;Shuiming Zhong
通过精确的突触效率调整方法有效训练有监督的尖峰神经网络
DOI：
10.1109/tnnls.2016.2541339
发表时间：
2017-06
影响因子：
10.4
作者：
Xiurui Xie;Hong Qu
通讯作者：
Hong Qu
影响因子：
2.9
作者：
H. Snippe
通讯作者：
H. Snippe
DOI：
--
发表时间：
2015
期刊：
--
影响因子：
--
作者：
S. Thorpe
通讯作者：
S. Thorpe