Understanding SyncMap: Analyzing the components of Its Dynamical Equation
Understanding SyncMap: Analyzing the components of Its Dynamical Equation
复制标题
理解SyncMap：分析其动态方程的组成部分
DOI：
--
复制
发表时间：
2022
期刊：
影响因子：
--
通讯作者：
Danilo Vasconcellos Vargas
中科院分区：
文献类型：
--
作者：
Tham Yik Foong;Danilo Vasconcellos Vargas
SycnMap最近被提出作为一种无监督的方法来执行组块。该模型属于福尔斯自组织动力学方程的范式，不需要任何目标函数，仅利用自组织原理即可实现学习。然而，由于它的新奇，人们对它的了解仍然很少。在这里，我们提供了一个全面的分析的基础动力学方程，支配SyncMap的学习。我们首先介绍了动力学方程的几个组成部分：（1）学习率，（2）动态噪声，（3）吸引力系数;以及模型特定的变量：（4）输入信号噪声和（5）权重空间的维数。有了这一点，我们研究它们对SyncMap性能的影响。我们的研究表明，动态噪声和权重空间的维数在动力学方程中起着重要的作用;通过单独调整它们，增强的模型可以在7个环境中的6个环境中优于基线方法和原始SyncMap。
SycnMap has been recently proposed as an unsupervised approach to perform chunking. This model, which falls under the paradigm of self-organizing dynamical equations, can achieve learning merely using the principle of self-organization without any objective function. However, it is still poorly understood due to its novelty. Here, we provide a comprehensive analysis of the underlying dynamical equation that governed the learning of SyncMap. We first introduce several components of the dynamical equation: (1) Learning rate, (2) Dynamic noise, and (3) Coefficient of attraction force; As well as model-specific variables: (4) Input signal noise and (5) Dimension of weight space. With that, we examine their effect on the performance of SyncMap. Our study shows that the dynamic noise and dimension of weight space play an important role in the dynamical equation; By solely tuning them, the enhanced model can outperform the baseline methods as well as the original SyncMap in 6 out of 7 environments.
DOI：
10.1037/0278-7393.31.6.1235
发表时间：
2005-11-01
影响因子：
2.6
作者：
Chen, ZJ;Cowan, N
通讯作者：
Cowan, N