arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2103.14516cs.LGcs.SYeess.SY
收藏

状态空间人工神经网络的改进学习算法

Improved Initialization of State-Space Artificial Neural Networks

Eindhoven University of Technology(埃因霍温理工大学)

Maarten Schoukens

摘要:

黑箱非线性状态空间模型的辨识需要状态和输出方程的灵活表示。人工神经网络已经证明可以提供这样的表示。然而,在许多识别问题中,需要解决非线性优化问题以获得模型参数(层权重和偏置)。这些模型参数的深思熟虑的初始化通常可以避免非线性优化算法收敛到所考虑的成本函数的表现不佳的局部最小值。本文介绍了一种改进的初始化方法表示为一个循环的人工神经网络的非线性状态空间模型,并强调在模型结构中包括一个显式的线性项的重要性。一些神经网络权重从非线性系统的线性近似开始初始化,而其他权重使用随机值或零初始化。所提出的初始化方法比以前提出的方法的有效性说明了两个基准的例子。

英文摘要:

The identification of black-box nonlinear state-space models requires a flexible representation of the state and output equation. Artificial neural networks have proven to provide such a representation. However, as in many identification problems, a nonlinear optimization problem needs to be solved to obtain the model parameters (layer weights and biases). A well-thought initialization of these model parameters can often avoid that the nonlinear optimization algorithm converges to a poorly performing local minimum of the considered cost function. This paper introduces an improved initialization approach for nonlinear state-space models represented as a recurrent artificial neural network and emphasizes the importance of including an explicit linear term in the model structure. Some of the neural network weights are initialized starting from a linear approximation of the nonlinear system, while others are initialized using random values or zeros. The effectiveness of the proposed initialization approach over previously proposed methods is illustrated on two benchmark examples.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑