基于自适应自然梯度法的在线高斯过程建模

Online learning algorithm of Gaussian process based on adaptive nature gradient

为了满足在线建模算法的实时性要求,提出了在高斯过程的训练中使用自适应自然梯度法(ANG),即基于自适应自然梯度法的在线高斯过程回归建模算法。将此算法运用在Micky-Glass系统和连续搅拌反应釜(CSTR)模型的建立中,并与稀疏在线高斯过程算法进行比较。仿真结果表明此算法满足了非线性系统建模的实时性和精度的要求,同时克服了其他方法计算量很大、不符合在线算法的实时性要求的缺点。

In order to satisfy the online modeling algorithm＇ s request of real-time, this paper proposed the adaptive natural gradient method used in online Gaussian process training. The algorithm was named online learning algorithm of Gaussian process based on adaptive nature gradient. The algorithm was applied in Micky-Glass system and continuous stirred tank reactor （CSTR） modeling,and compared with the sparse online Ganssian processes algorithm. Obtained from the simulation results, this algorithm meets the real-time and accuracy requirements of nonlinear system modeling, and overcomes other online algorithms＇ faults of needing much computation resource and not to accord with the requirement of real-time of online algorithm.