Unsupervised learning of digit recognition using spike-timing-dependent plasticity.
Unsupervised learning of digit recognition using spike-timing-dependent plasticity.
复制标题
DOI：
10.3389/fncom.2015.00099
复制
发表时间：
2015
影响因子：
3.2
通讯作者：
Cook M
中科院分区：
文献类型：
--
作者：
Diehl PU;Cook M
为了理解哺乳动物的新皮层是如何执行计算的，有两件事是必要的：我们需要很好地理解可用的神经元处理单元和机制，我们需要更好地理解这些机制是如何结合起来构建功能系统的。因此，近年来，人们对如何使用尖峰神经网络（SNN）来执行复杂计算或解决模式识别任务越来越感兴趣。然而，设计使用生物学上合理的机制（特别是用于学习新模式）的SNN仍然是一项具有挑战性的任务，因为大多数这样的SNN架构依赖于基于速率的网络中的训练以及随后向SNN的转换。我们提出了一个SNN的数字识别，这是基于机制与增加的生物相容性，即，基于电导而不是基于电流的突触、具有时间依赖性权重变化的尖峰定时依赖性可塑性、侧抑制和自适应尖峰阈值。与大多数其他系统不同，我们不使用教学信号，也不向网络提供任何类别标签。使用这种无监督学习方案，我们的架构在MNIST基准测试中达到了95%的准确率，这比以前没有监督的SNN实现要好。我们没有使用特定领域的知识，这一事实表明我们的网络设计具有普遍适用性。此外，我们的网络的性能与所使用的神经元数量很好地匹配，并且对于四种不同的学习规则显示出相似的性能，这表明了机制的完整组合的鲁棒性，这表明了异构生物神经网络的适用性。
In order to understand how the mammalian neocortex is performing computations, two things are necessary; we need to have a good understanding of the available neuronal processing units and mechanisms, and we need to gain a better understanding of how those mechanisms are combined to build functioning systems. Therefore, in recent years there is an increasing interest in how spiking neural networks (SNN) can be used to perform complex computations or solve pattern recognition tasks. However, it remains a challenging task to design SNNs which use biologically plausible mechanisms (especially for learning new patterns), since most such SNN architectures rely on training in a rate-based network and subsequent conversion to a SNN. We present a SNN for digit recognition which is based on mechanisms with increased biological plausibility, i.e., conductance-based instead of current-based synapses, spike-timing-dependent plasticity with time-dependent weight change, lateral inhibition, and an adaptive spiking threshold. Unlike most other systems, we do not use a teaching signal and do not present any class labels to the network. Using this unsupervised learning scheme, our architecture achieves 95% accuracy on the MNIST benchmark, which is better than previous SNN implementations without supervision. The fact that we used no domain-specific knowledge points toward the general applicability of our network design. Also, the performance of our network scales well with the number of neurons used and shows similar performance for four different learning rules, indicating robustness of the full combination of mechanisms, which suggests applicability in heterogeneous biological neural networks.