arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2106.03078cs.LG
收藏

一种用于非线性系统辨识的新型深度神经网络结构

A novel Deep Neural Network architecture for non-linear system identification

University of Padova(帕多瓦大学)

Luca Zancato, Alessandro Chiuso

摘要:

提出了一种用于非线性系统辨识的新型深度神经网络(DNN)架构。我们通过限制DNN的表示能力来促进泛化。为了做到这一点,受衰落记忆系统的启发,我们引入了归纳偏置(在架构上)和正则化(在损失函数上)。该架构允许仅基于可用数据的自动复杂度选择,以这种方式减少了必须由用户选择的超参数的数量。利用高度并行化的DNN框架(基于随机优化方法),我们成功地将我们的方法应用于大规模数据集。

英文摘要:

We present a novel Deep Neural Network (DNN) architecture for non-linear system identification. We foster generalization by constraining DNN representational power. To do so, inspired by fading memory systems, we introduce inductive bias (on the architecture) and regularization (on the loss function). This architecture allows for automatic complexity selection based solely on available data, in this way the number of hyper-parameters that must be chosen by the user is reduced. Exploiting the highly parallelizable DNN framework (based on Stochastic optimization methods) we successfully apply our method to large scale datasets.

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。

↑