Cachi Paolo G, Ventura Sebastián, Cios Krzysztof J
Department of Computer Science, Virginia Commonwealth University, Richmond, VA, United States.
Department of Computer Science, Universidad de Córdoba, Córdoba, Spain.
Front Comput Neurosci. 2021 Apr 22;15:627567. doi: 10.3389/fncom.2021.627567. eCollection 2021.
In this paper we present a Competitive Rate-Based Algorithm (CRBA) that approximates operation of a Competitive Spiking Neural Network (CSNN). CRBA is based on modeling of the competition between neurons during a sample presentation, which can be reduced to ranking of the neurons based on a dot product operation and the use of a discrete Expectation Maximization algorithm; the latter is equivalent to the spike time-dependent plasticity rule. CRBA's performance is compared with that of CSNN on the MNIST and Fashion-MNIST datasets. The results show that CRBA performs on par with CSNN, while using three orders of magnitude less computational time. Importantly, we show that the weights and firing thresholds learned by CRBA can be used to initialize CSNN's parameters that results in its much more efficient operation.
在本文中，我们提出了一种基于竞争率的算法（CRBA），该算法可近似竞争脉冲神经网络（CSNN）的运行。CRBA基于对样本呈现期间神经元之间竞争的建模，这可以简化为基于点积运算对神经元进行排序，并使用离散期望最大化算法；后者等同于脉冲时间依赖可塑性规则。在MNIST和Fashion-MNIST数据集上，将CRBA的性能与CSNN的性能进行了比较。结果表明，CRBA的性能与CSNN相当，同时计算时间少三个数量级。重要的是，我们表明，CRBA学习到的权重和发放阈值可用于初始化CSNN的参数，从而使其运行效率更高。
