Supervised Learning in Spiking Neural Networks for Precise Temporal Encoding.
Supervised Learning in Spiking Neural Networks for Precise Temporal Encoding.
复制标题
DOI：
10.1371/journal.pone.0161335
复制
发表时间：
2016
期刊：
影响因子：
3.7
通讯作者：
Grüning A
中科院分区：
文献类型：
--
作者：
Gardner B;Grüning A
精确的尖峰定时作为神经网络中信息编码的一种手段得到了生物学的支持，并且通过在更短的时间尺度上处理输入特征，它比基于频率的编码更有优势。由于这些原因，最近的注意力集中在利用时间编码方案的尖峰神经网络的监督学习规则的开发上。然而，尽管这一领域取得了重大进展，但仍然缺乏有理论基础且可被认为具有生物学相关性的规则。在这里，我们研究了突触可塑性最有效地发生以支持精确时间代码的监督学习的一般条件。作为分析的一部分，我们研究了两种基于尖峰的学习方法：其中一种依赖于瞬时误差信号来修改网络中的突触权重（INST 规则），另一种依赖于过滤后的误差信号来实现更平滑的突触权重修改（FILT 规则）。我们测试每个规则提供的解决方案在时间编码精度方面的准确性，然后使用单个尖峰的精确计时作为其存储容量的指示来测量它们可以学习记住的输入模式的最大数量。我们的结果证明了 FILT 规则在大多数情况下都具有高性能，这得益于该规则的错误过滤机制，预计该规则将在学习过程中平滑收敛到所需的解决方案。我们还发现 FILT 规则在执行输入模式记忆方面最为有效，并且在使用具有亚毫秒时间精度的尖峰来识别模式时最为明显。与现有工作相比，我们确定 FILT 规则的性能与高效电子学习 Chronotron 规则的性能一致，但具有明显的优势，我们的 FILT 规则也可以作为提高生物真实性的在线方法来实现。
Precise spike timing as a means to encode information in neural networks is biologically supported, and is advantageous over frequency-based codes by processing input features on a much shorter time-scale. For these reasons, much recent attention has been focused on the development of supervised learning rules for spiking neural networks that utilise a temporal coding scheme. However, despite significant progress in this area, there still lack rules that have a theoretical basis, and yet can be considered biologically relevant. Here we examine the general conditions under which synaptic plasticity most effectively takes place to support the supervised learning of a precise temporal code. As part of our analysis we examine two spike-based learning methods: one of which relies on an instantaneous error signal to modify synaptic weights in a network (INST rule), and the other one relying on a filtered error signal for smoother synaptic weight modifications (FILT rule). We test the accuracy of the solutions provided by each rule with respect to their temporal encoding precision, and then measure the maximum number of input patterns they can learn to memorise using the precise timings of individual spikes as an indication of their storage capacity. Our results demonstrate the high performance of the FILT rule in most cases, underpinned by the rule’s error-filtering mechanism, which is predicted to provide smooth convergence towards a desired solution during learning. We also find the FILT rule to be most efficient at performing input pattern memorisations, and most noticeably when patterns are identified using spikes with sub-millisecond temporal precision. In comparison with existing work, we determine the performance of the FILT rule to be consistent with that of the highly efficient E-learning Chronotron rule, but with the distinct advantage that our FILT rule is also implementable as an online method for increased biological realism.