An unsupervised neuromorphic clustering algorithm
An unsupervised neuromorphic clustering algorithm
复制标题
DOI：
10.1007/s00422-019-00797-7
复制
发表时间：
2019-08-01
影响因子：
1.9
通讯作者：
Nowotny, Thomas
中科院分区：
文献类型：
--
作者：
Diamond, Alan;Schmuker, Michael;Nowotny, Thomas
大脑执行复杂任务所需的功率仅为传统计算机执行相同任务所需的一小部分。新的神经形态硬件系统现在正变得广泛可用，旨在模拟大脑的更节能，高度并行操作。然而，要在应用程序中使用这些系统，我们需要可以在其上运行的神经形态算法。在这里，我们开发了一个尖峰神经网络模型的神经形态硬件，使用尖峰时间依赖的可塑性和侧抑制进行无监督聚类。利用该模型，时不变的、速率编码的数据集可以被映射到具有指定分辨率的特征空间，即，集群的数量，专门使用神经形态硬件。我们开发并测试了SpiNNaker神经形态系统和使用GeNN框架的GPU上的实现。我们表明，我们的神经形态聚类算法实现的结果相比，传统的聚类算法，如自组织映射，神经气体或k-均值聚类。然后，我们结合联合收割机，它与以前报道的监督神经形态分类器网络，以证明其作为一个神经形态预处理模块的实际用途。
Brains perform complex tasks using a fraction of the power that would be required to do the same on a conventional computer. New neuromorphic hardware systems are now becoming widely available that are intended to emulate the more power efficient, highly parallel operation of brains. However, to use these systems in applications, we need neuromorphic algorithms that can run on them. Here we develop a spiking neural network model for neuromorphic hardware that uses spike timing-dependent plasticity and lateral inhibition to perform unsupervised clustering. With this model, time-invariant, rate-coded datasets can be mapped into a feature space with a specified resolution, i.e., number of clusters, using exclusively neuromorphic hardware. We developed and tested implementations on the SpiNNaker neuromorphic system and on GPUs using the GeNN framework. We show that our neuromorphic clustering algorithm achieves results comparable to those of conventional clustering algorithms such as self-organizing maps, neural gas or k-means clustering. We then combine it with a previously reported supervised neuromorphic classifier network to demonstrate its practical use as a neuromorphic preprocessing module.