检索结果-内蒙古大学图书馆

Quantized gradient-descent algorithm for Distributed Resource Allocation

UNMANNED SYSTEMS 2019年第2期7卷 119-136页

作者： Zhou, Hongbing Yu, Weiyong Yi, Peng Hong, Yiguang Nanyang Normal Univ Sch Math & Stat 1638 Wolong Rd Nanyang Henan Peoples R China Beijing Econ & Technol Dev Area BDA JD Grp 18 Kechaung 11 St Beijing Peoples R China Washington Univ Dept Elect & Syst Engn 1 Brookings Dr St Louis MO 63130 USA Chinese Acad Sci Inst Syst Sci Key Lab Syst & Control 55 Zhongguancun East Rd Beijing Peoples R China Univ Chinese Acad Sci 55 Zhongguancun East Rd Beijing Peoples R China

In this paper, we consider a distributed resource allocation problem with communication limitation. We propose a gradient-descent algorithm to solve the distributed resource allocation problem with quantization mechanism due to the communication limitations or in order to reduce the communication cost in the network. With carefully selected parameters, the convergence and correctness of the quantized algorithm can be obtained for fixed communication topologies and moreover, extended to switching jointly connected topologies. The exact optimal value can be obtained, which is different from some existing works, whose convergence accuracies were limited by the quantization bandwidth. In addition, the data rate of the proposed algorithm is also analyzed for both fixed and switching communication networks. Particularly, in the fixed topology case, we obtain that 1 bit is sufficient to solve the distributed problem with the proposed algorithm.

关键词： Distributed optimization gradient-descent algorithm quantization resource allocation

来源：评论

学校读者我要写书评

暂无评论

Enhancing Hopfield network performance for pattern retrieval using sparse recovery algorithm and Parzen estimator

引用

DIGITAL SIGNAL PROCESSING 2025年 156卷

作者： Stankovic, Djordje Draganic, Andjela Ioana, Cornel Orovic, Irena Univ Montenegro Fac Elect Engn Podgorica Montenegro Grenoble Inst Technol Grenoble INP GIPSA Lab 11 Rue MathGrenoble Campus BP46 F-38402 Grenoble Isere France Univ Lusofona COPELABS P-1700097 Lisbon Portugal

An improved pattern recovery approach that integrates the Hopfield neural network (HNN) with the iterative signal reconstruction and Parzen window-based classification is proposed. The HNN is observed as a form of associative memory network, used for various pattern recognition and optimization tasks. However, when the input pattern is highly damaged with a very limited set of available samples, the Hopfield network fails to perform the retrieval. The convex optimization-based gradient descent algorithm is considered for pattern recovery of damaged inputs in order to provide an improved pattern approximation for further processing within the HNN, enabling successful network performance. Additionally, in the case of grayscale images, the Parzen window approach is used to classify the probability density functions (pdfs) of the training set and to choose those being comparable to the pdf of the input pattern, therefore refining the selection of patterns and providing better convergence to the exact retrieval. The theoretical considerations are verified experimentally, showing the high performance of the proposed approach when only 10 % of the pixels are available for binary patterns and 40 % of pixels for grayscale patterns.

关键词： gradient-descent algorithm Hopfield neural network Parzen estimator Pattern retrieval Iterative signal recovery

来源：评论

学校读者我要写书评

暂无评论

End-to-end training algorithm for conceptor-based neural networks

引用

ELECTRONICS LETTERS 2018年第15期54卷 924-925页

作者： Qian, Guangwu Zhang, Lei Zhang, Qianjun Sichuan Univ Coll Comp Sci Machine Intelligence Lab Chengdu Sichuan Peoples R China

Since a conceptor, achieving direction-selective damping of high-dimensional network signals, usually takes the form of a projection matrix and is deduced analytically, a conceptor-based neural network is thought to be untrainable with backpropagation and gradient-descent algorithms from end to end. It limits the application of conceptors. To address this issue, an algorithm is proposed to train conceptor-based neural networks from end to end with gradient-descent algorithms. To the best of the authors' knowledge, it is the first work of such an end-to-end training algorithm. To develop this algorithm, a softmax-like loss function involved with conceptors is constructed empirically. Based on this loss function, corresponding gradients are deduced by using backpropagation method so that it is possible to train conceptor neural networks from end to end with a gradient-descent algorithm. Several experiments are conducted to show the feasibility and effectiveness of the proposed training algorithm.

关键词： recurrent neural nets backpropagation gradient methods matrix algebra end-to-end training algorithm conceptor-based neural networks direction-selective damping high-dimensional network signals projection matrix backpropagation algorithm gradient-descent algorithm softmax-like loss function recurrent neural networks

来源：评论

学校读者我要写书评

暂无评论

Soft-Sensor of Ozone Concentration in Ozone Generation System

引用

OZONE-SCIENCE & ENGINEERING 2010年第1期32卷 56-60页

作者： Zhang, Haichuan Liu, Zhongyang Xu, Dongwei Wang, Ninghui Dalian Univ Technol Dept Elect & Elect Engn Dalian 116024 Peoples R China

The soft-sensor of ozone concentration is introduced. Six secondary variables are chosen in the soft-sensor model. The model is built based on the radial basis function neural network and its parameters are confirmed by the gradient-descent algorithm. The model is implemented on the basis of the monitoring system that is necessary for ozone generation;thus, it requires no additional hardware cost. The response time of the model is less than 0.6 seconds. The experimental results indicate that the relative errors of the soft-sensor are less than 5%.

关键词： Ozone Ozone Concentration Soft-Sensor Model Radial Basis Function Neural Network gradient-descent algorithm

来源：评论

学校读者我要写书评

暂无评论

Automated Optimization algorithm for 16-channel Silicon WDM System Using 4-Level Cascaded Mach-Zehnder Interferometers

Automated Optimization Algorithm for 16-channel Silicon WDM ...

引用

Asia Communications and Photonics Conference (ACP) / International Conference on Information Photonics and Optical Communications (IPOC)

作者： Wu, Yichen Tao, Zihan Yang, Qipeng Shen, Bitao Jin, Ming Shu, Haowen Bai, Bowen Wang, Xingjun Peking Univ Sch Elect State Key Lab Adv Opt Commun Syst & Networks Beijing 100871 Peoples R China Peking Univ Frontier Sci Ctr Nano Optoelect Beijing 100871 Peoples R China Peking Univ Yangtze Delta Inst Optoelect Nantong 226010 Peoples R China Peng Cheng Lab Shenzhen 518055 Peoples R China

ISBN: (纸本)9781665481557

On-chip Wavelength Division Multiplexing (WDM) devices have been widely used in optical communications and signal processing to increase data throughput. As the number of wavelength channels increases, the performance of WDM devices is susceptible to various types of errors from fabrication, design and environmental changes. To address this issue, we demonstrate an automated optimization control method based on the gradient-descent algorithm and examine the performance of applying this algorithm to a silicon photonic 16-channel WDM device utilizing 4-level cascaded tunable MachZehnder interferometers. The extinction ratio and crosstalk of all 16 channels are successfully optimized with different initial temperatures in simulation. This procedure provides a general approach to automated control and optimize complex photonic systems.

关键词： Silicon Photonics gradient-descent algorithm Wavelength Division Mach-Zehnder Interferometers

来源：评论

学校读者我要写书评

暂无评论

Ordinal Classification Using Hybrid Artificial Neural Networks with Projection and Kernel Basis Functions

引用

7th International Conference on Hybrid Artificial Intelligent Systems (HAIS)

作者： Dorado-Moreno, M. Gutierrez, P. A. Hervas-Martinez, C. Univ Cordoba Dept Comp Sci & Numer Anal E-14071 Cordoba Spain

ISBN: (纸本)9783642289309;9783642289316

Many real life problems require the classification of items into naturally ordered classes. These problems are traditionally handled by conventional methods intended for the classification of nominal classes, where the order relation is ignored. This paper proposes a hybrid neural network model applied to ordinal classification using a possible combination of projection functions (product unit, PU) and kernel functions (radial basis function, RBF) in the hidden layer of a feed-forward neural network. A combination of an evolutionary and a gradient-descent algorithms is adapted to this model and applied to obtain an optimal architecture, weights and node typology of the model. This combined basis function model is compared to the corresponding pure models: PU neural network, and the RBF neural network. Combined functions using projection and kernel functions are found to be better than pure basis functions for the task of ordinal classification in several datasets.

关键词： Ordinal Classification Projection basis functions Kernel basis functions Evolutionary neural networks Evolutionary algorithm gradient-descent algorithm

来源：评论

学校读者我要写书评

暂无评论

Real-time Optimal Power Allocation for Smart Grid System via Deep Neural Network: A Learning Based Approach 32

Real-time Optimal Power Allocation for Smart Grid System via...

引用

32nd Chinese Control And Decision Conference (CCDC)

作者： Guo, Fanghong Xu, Bowen Zhang, Wen-An Zhang, Dan Yu, Li Zhejiang Univ Technol Dept Automat Hangzhou 310032 Peoples R China

ISBN: (纸本)9781728158556

This paper attempts to solve the optimal power allocation (OPA) problem for smart grid system in a new distinguished way. Conventionally the numerical optimization approaches including traditional convex optimization and heuristic search methods almost occupy the addressing of such problem. However, these optimization algorithms may suffer from high computational complexity when the system scales up, which would inevitably create a gap between the theoretical algorithm design and real-time algorithm implementation. In this paper, we aim to provide a new learning based approach to handle the real-time OPA problem in smart grid system. The key idea behind this approach is to treat the input and output of traditional OPA optimization algorithm as an unknown nonlinear mapping, which is then approximated by recent popular learning based tools such as deep neural network (DNN). As long as the constructed DNN can accurately learn such nonlinear mapping, then the OPA problem can be solved in real time. Our main contribution is to theoretically show that the traditional decentralized gradient-based optimization algorithm for OPA problem can be accurately approximated by a well-constructed DNN. Furthermore, experimental case studies validate the effectiveness and advantages of our proposed method.

关键词： Learning to optimize deep neural networks optimal power allocation gradient-descent algorithm power system

来源：评论

学校读者我要写书评

暂无评论

Denoising Signals in Cognitive Radio Systems Using An Evolutionary algorithm Based Adaptive Filter 7

Denoising Signals in Cognitive Radio Systems Using An Evolut...

引用

7th IEEE Annual Ubiquitous Computing, Electronics and Mobile Communication Conference (IEEE UEMCON)

作者： Quadri, Adnan Manesh, Mohsen Riahi Kaabouch, Naima Univ North Dakota Dept Elect Engn Grand Forks ND 58203 USA

ISBN: (纸本)9781509014965

Noise originating from several sources in a RF environment degrades the performance of communication systems. In wideband systems, such as cognitive radios, noise at the receiver can also originate from non-linearity present in the RF front end, time-varying thermal noise within the receiver radio system, and noise from adjacent network nodes. Several denoising techniques have been proposed for cognitive radios, some of which are applied during spectrum sensing and others to received noisy signals. Examples of these techniques include least mean square (LMS) and its variants. However, these algorithms have low performance with non-linear signals and cannot locate the global optimum solution for noise cancellation. Therefore, application of global search optimization techniques, such as evolutionary algorithms, is considered for noise cancellation. In this paper, particle swarm optimization (PSO) and LMS algorithms are implemented and their performances compared. Extensive simulations were performed where Gaussian and nonlinear random noise were added to the transmitted signals. The performance comparison was done using two metrics: bit error rate and mean square error. The results show that PSO outperforms LMS under both Gaussian and non-linear random noise.

关键词： adaptive noise cancellation evolutionary algorithm gradient-descent algorithm cognitive radio adaptive filter particle swarm optimization least mean square

来源：评论

学校读者我要写书评

暂无评论

Block versus Adaptive MIMO Equalization for Coherent PolMux QAM Transmission Systems

Block versus Adaptive MIMO Equalization for Coherent PolMux ...

引用

36th European Conference and Exhibition on Optical Communication (ECOC)

作者： Selmi, Mehrez Ciblat, Philippe Jaoueen, Yves Gosset, Christophe Telecom ParisTech CNRS UMR 5141 Inst Telecom F-75634 Paris France

We propose a block equalization algorithm using optimal step size. The algorithm shows fast convergence, low steady-state error and good tracking capacity in comparison to standard equalizers operating on a sample-by-... 详细信息

ISBN: (纸本)9781424485369;9781424485345

关键词： MIMO communication adaptive MIMO equalization adaptive equalisers block equalization algorithm coherent PolMux QAM transmission systems gradient methods gradient-descent algorithm low steady-state error multiplexing optical communication optical modulation optimal step size polarization multiplexing quadrature amplitude modulation

来源：评论

学校读者我要写书评

暂无评论

A Takagi-Sugeno fuzzy controller with reinforcement learning part

A Takagi-Sugeno fuzzy controller with reinforcement learning...

引用

International Conference on Neural Networks and Signal Processing

作者： Liu, XH Jin, DM Tsing Hua Univ Inst Microelect Beijing 100084 Peoples R China

ISBN: (纸本)0780377028

A Takagi-Sugeno fuzzy controller with reinforcement learning part is proposed in this paper, which is used to control a real inverted cart-pendulum system. The fuzzy controller part is a zero-order Takagi-Sugeno system with four inputs and one output. The learning part is based on the gradient-descent algorithm which modifies the consequent parameters of the fuzzy rules. Because the expected output values are unknown, a reinforcement signal instead of the output error is used in learning process. The reinforcement signal is decided by the judgment of whether the action should be punished or rewarded and the degree of punishments or rewards. The performance of controlling a real inverted cart-pendulum system proves the validity and the superiority of the proposed fuzzy controller with reinforcement learning part.

关键词： fuzzy control pendulums position control learning (artificial intelligence) nonlinear control systems gradient methods Takagi-Sugeno fuzzy controller reinforcement learning part gradient-descent algorithm inverted cart-pendulum system

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：