Knowledge Engineering & Discovery Research Institute (KEDRI), Auckland University of Technology, New Zealand.
Neural Netw. 2013 May;41:188-201. doi: 10.1016/j.neunet.2012.11.014. Epub 2012 Dec 20.
On-line learning and recognition of spatio- and spectro-temporal data (SSTD) is a very challenging task and an important one for the future development of autonomous machine learning systems with broad applications. Models based on spiking neural networks (SNN) have already proved their potential in capturing spatial and temporal data. One class of them, the evolving SNN (eSNN), uses a one-pass rank-order learning mechanism and a strategy to evolve a new spiking neuron and new connections to learn new patterns from incoming data. So far these networks have been mainly used for fast image and speech frame-based recognition. Alternative spike-time learning methods, such as Spike-Timing Dependent Plasticity (STDP) and its variant Spike Driven Synaptic Plasticity (SDSP), can also be used to learn spatio-temporal representations, but they usually require many iterations in an unsupervised or semi-supervised mode of learning. This paper introduces a new class of eSNN, dynamic eSNN, that utilise both rank-order learning and dynamic synapses to learn SSTD in a fast, on-line mode. The paper also introduces a new model called deSNN, that utilises rank-order learning and SDSP spike-time learning in unsupervised, supervised, or semi-supervised modes. The SDSP learning is used to evolve dynamically the network changing connection weights that capture spatio-temporal spike data clusters both during training and during recall. The new deSNN model is first illustrated on simple examples and then applied on two case study applications: (1) moving object recognition using address-event representation (AER) with data collected using a silicon retina device; (2) EEG SSTD recognition for brain-computer interfaces. The deSNN models resulted in a superior performance in terms of accuracy and speed when compared with other SNN models that use either rank-order or STDP learning. The reason is that the deSNN makes use of both the information contained in the order of the first input spikes (which information is explicitly present in input data streams and would be crucial to consider in some tasks) and of the information contained in the timing of the following spikes that is learned by the dynamic synapses as a whole spatio-temporal pattern.
基于尖峰神经元网络（SNN）的模型已被证明在捕获时空数据方面具有潜力。其中一类称为进化 SNN（eSNN），它使用单遍排序学习机制和一种策略来进化新的尖峰神经元和新的连接，以便从传入的数据中学习新的模式。到目前为止，这些网络主要用于快速的图像和语音帧识别。替代的尖峰时间学习方法，如尖峰时间依赖可塑性（STDP）及其变体尖峰驱动突触可塑性（SDSP），也可以用于学习时空表示，但它们通常需要在无监督或半监督的学习模式下进行多次迭代。本文介绍了一类新的 eSNN，称为动态 eSNN，它利用排序学习和动态突触在快速的在线模式下学习 SSTD。本文还介绍了一种新的模型称为 deSNN，它在无监督、监督或半监督模式下利用排序学习和 SDSP 尖峰时间学习。SDSP 学习用于动态进化网络，改变连接权重，在训练和回忆过程中捕获时空尖峰数据聚类。新的 deSNN 模型首先在简单的示例上进行说明，然后应用于两个案例研究应用程序：（1）使用硅视网膜设备收集的数据，使用事件地址表示（AER）进行移动物体识别；（2）用于脑机接口的 EEG SSTD 识别。与使用排序或 STDP 学习的其他 SNN 模型相比，deSNN 模型在准确性和速度方面表现出更好的性能。原因是 deSNN 利用了输入尖峰的顺序中包含的信息（这种信息在输入数据流中明确存在，在某些任务中至关重要），以及由动态突触作为整体时空模式学习到的后续尖峰时间包含的信息。
