شناسایی سیستم های غیر خطی با استفاده از شبکه های عصبی کانولوشن
ترجمه نشده

شناسایی سیستم های غیر خطی با استفاده از شبکه های عصبی کانولوشن

عنوان فارسی مقاله: تاثیر وزن های تصادفی بر روی شناسایی سیستم های غیر خطی با استفاده از شبکه های عصبی کانولوشن
عنوان انگلیسی مقاله: Impact of random weights on nonlinear system identification using convolutional neural networks
مجله/کنفرانس: علوم اطلاعات - Information Sciences
رشته های تحصیلی مرتبط: مهندسی کامپیوتر، فناوری اطلاعات
گرایش های تحصیلی مرتبط: مهندسی الگوریتم، هوش مصنوعی، شبکه های کامپیوتری
کلمات کلیدی فارسی: شبکه عصبی کانولوشن، الگوریتم های تصادفی، دامنه فرکانس، یادگیری عمیق
کلمات کلیدی انگلیسی: Convolutional neural network، Random algorithms، Frequency domain، Deep learning
نوع نگارش مقاله: مقاله پژوهشی (Research Article)
شناسه دیجیتال (DOI): https://doi.org/10.1016/j.ins.2018.10.019
دانشگاه: Departamento de Control Automatico, CINVESTAV-IPN (National Polytechnic Institute), Av.IPN 2508, Mexico City 07360, Mexico
صفحات مقاله انگلیسی: 26
ناشر: الزویر - Elsevier
نوع ارائه مقاله: ژورنال
نوع مقاله: ISI
سال انتشار مقاله: 2019
ایمپکت فاکتور: 5/080 در سال 2017
شاخص H_index: 142 در سال 2019
شاخص SJR: 1/635 در سال 2017
شناسه ISSN: 0020-0255
شاخص Quartile (چارک): Q1 در سال 2017
فرمت مقاله انگلیسی: PDF
وضعیت ترجمه: ترجمه نشده است
قیمت مقاله انگلیسی: رایگان
آیا این مقاله بیس است: بله
کد محصول: E10892
فهرست مطالب (انگلیسی)

Abstract

1- Introduction

2- Convolutional neural networks for system modeling

3- Frequency domain analysis of random weights

4- CNN training with random weights

5- Simulations

6- Conclusion

References

بخشی از مقاله (انگلیسی)

Abstract

Randomized algorithms have been successfully applied in modelling dynamic system. How do random weights affect system identification and why do they sometimes work well? In this paper, we use the convolutional neural network (CNN) as an identification model to answer these questions. Since the convolution operation is an important property of the dynamic system and in the frequency domain it becomes the product, the CNN model is analyzed in the frequency domain. We first modify the CNN model, so that it can model both the input and the output series. Then we analyze the impact of the random weights of CNN in the frequency domain. We prove the existence of optimal weights and analyze the modeling accuracy under optimal weights and random weights. Through theoretical analysis, we propose a two-step training method and compare it with the random weight algorithm. The proposed CNN model with random weights is validated with three benchmark problems.

Introduction

To predict the future behavior of the dynamic system, to apply model-based control or to understand the physical process, system identification is needed. Neural networks are black box models, which only use input and output data. These data-based modeling methods still have many problems. The hyper-parameters must be defined before they are applied, for example, how many hidden layers and hidden nodes are needed [21]. The universal approximation theorem guarantees that the neural model can approach almost all continuous systems with enough hidden nodes, however, the fact of increasing the hidden nodes causes the over-fit problem [34]. The alternative method to increase the hidden nodes is to use more hidden layers. It is a basic idea of deep neural networks. Theory and application show that deep learning models achieve better training precision [2], and get impressive results on many difficult tasks [14]. The convolutional neural network (CNN) is one of the most important deep learning models [22][33]. The main difference between CNN and normal neural networks is the convolution operation. The first successful CNN is at early 90s for the classification of digits [23], which includes the invariances in two-dimensional forms using local connections and weight restrictions. The training uses the maximum likelihood estimation and the modified backpropagation algorithm [26]. To give a better understanding of how convolutional networks work, [39] proposed the de-convolutional technique to visualize the operations of the hidden layer. By using GPU (Graphic Processing Unit), faster learning and testing are obtained by [20]. It has been proven that CNNs have great performances in classification tasks, such as image processing [30]. CNNs are also applied for data regression and time series modeling. In [4], the time series is formed in the autoregressive model. In [12], CNN is applied to classify the time series.