linear dimensionality reduction methods are commonly used to extract low-dimensional structure from high-dimensional data. However, popular methods disregard temporal structure, rendering them prone to extracting
本研究提出了一种在最大后验(MAP)框架下,采用基于一般化梯度下降法的期望最大化(EM)算法,对线性动态系统的转移矩阵进行L1正则化来减轻隐藏状态数量选择问题的方法,这种 Sparse Linear Dynamical System (SLDS) 增强了对于临床多元时间序列数据的预测性能,相较于普通LDS模型。