检索结果-内蒙古大学图书馆

Listwise approach based on the cross-correntropy for learning to rank

ELECTRONICS LETTERS 2018年第14期54卷 878-879页

作者： Wu, Mintao Zhu, Jihua Wang, Jun Pang, Shanmin Li, Yaochen Xi An Jiao Tong Univ Sch Software Engn Xian 710049 Shaanxi Peoples R China Jiangnan Univ Sch Digital Media Wuxi 214122 Peoples R China

The problem of learning to rank is addressed and a novel listwise approach by taking document retrieval as an example is proposed. It first introduces the concept of cross-correntropy into learning to rank and then proposes the listwise loss function based on the cross-correntropy between the ranking list given by the label and the one predicted by training model. The use of the cross-correntropy loss leads to the development of the listwise approach called ListCCE, which employs the gradient descent algorithm to train a neural network model. Experimental results tested on publicly available data sets show that the proposed approach performs better than some existing approaches.

关键词： information retrieval learning (artificial intelligence) entropy gradient methods listwise approach cross-correntropy loss learning to rank document retrieval listwise loss function training model ListCCE gradient descent algorithm neural network model

来源：评论

学校读者我要写书评

暂无评论

A modified hybrid neural network for pattern recognition and its application to SSW complex in EEG

引用

NEURAL COMPUTING & APPLICATIONS 2006年第1期15卷 49-54页

作者： Acir, N Nigde Univ Dept Elect & Elect Engn TR-51245 Nigde Turkey

In this study, a modified hybrid neural network with asymmetric basis functions is presented for feature extraction of spike and slow wave complexes in electroencephalography (EEG). Feature extraction process has a great importance in all pattern recognition and classification problems. A gradient descent algorithm, indeed a back propagation type, is adapted to the proposed artificial neural network. The performance of the proposed network is measured using a support vector machine classifier fed by features extracted using the proposed neural network. The results show that the proposed neural network model can effectively be used in pattern recognition tasks. In experiments, real EEG data are used.

关键词： gradient descent algorithm feature extraction asymmetric basis functions electroencephalography

来源：评论

学校读者我要写书评

暂无评论

Convergence and gradient algorithm of a class of neural networks based on the polygonal fuzzy numbers representation

引用

COMPLEX & INTELLIGENT SYSTEMS 2022年第3期8卷 2383-2404页

作者： Sun, Gang Wang, Mingxin Li, Xiaoping Hunan Inst Technol Sch Sci Hengyang 421002 Peoples R China Tianjin Normal Univ Sch Management Tianjin 300387 Peoples R China

As a special case of general fuzzy numbers, the polygonal fuzzy number can describe a fuzzy object by means of an ordered representation of finite real numbers. Different from general fuzzy numbers, the polygonal fuzzy numbers overcome the shortcoming of complex operations based on Zadeh's traditional expansion principle, and can maintain the closeness of arithmetic operation. Hence, it is feasible to use a polygonal fuzzy number to approximate a general fuzzy number. First, an extension theorem of continuous functions on a real compact set is given according to open set construction theorem. Then using Weierstrass approximation theorem and ordered representation of the polygonal fuzzy numbers, the convergence of a single hidden layer feedforward polygonal fuzzy neural network is proved. Secondly, the gradient vector of the approximation error function and the optimization parameter vector of the network are given by using the ordered representation of polygonal fuzzy numbers, and then the gradient descent algorithm is used to train the optimal parameters of the polygonal fuzzy neural network iteratively. Finally, two simulation examples are given to verify the approximation ability of the network. Simulation result shows that the proposed network and the gradient descent algorithm are effective, and the single hidden layer feedforward network have good abilities in learning and generalization.

关键词： n-polygonal fuzzy numbers Ordered representation Polygonal neural network Convergence gradient descent algorithm

来源：评论

学校读者我要写书评

暂无评论

Experimental testing of a random neural network smart controller using a single zone test chamber

引用

IET NETWORKS 2015年第6期4卷 350-358页

作者： Javed, Abbas Larijani, Hadi Ahmadinia, Ali Emmanuel, Rohinton Gibson, Des Clark, Caspar Glasgow Caledonian Univ Sch Engn & Built Environm Glasgow Lanark Scotland Gas Sensing Solut Ltd Glasgow G68 9HQ Lanark Scotland Univ West Scotland Scottish Univ Phys Alliance Inst Thin Films Sensors & Imaging Paisley PA12BE Renfrew Scotland

Monitoring and analysis of energy use and indoor environmental conditions is an urgent need in large buildings to respond to changing conditions in an efficient manner. Correct estimation of occupancy will further improve energy performance. In this work, a smart controller for maintaining a comfortable environment using multiple random neural networks (RNNs) has been developed. The implementation of RNN-based controller is demonstrated to be more efficient on hardware and requires less memory compared to both artificial neural networks and model predictive controllers. This controller estimates the number of room occupants by using the information from wireless sensor nodes placed in the Heating, Ventilation and Air Conditioning (HVAC) duct and the room. For an occupied room, the controller can switch between thermal comfort mode (based on predicted mean vote set points) and user defined mode (i.e. occupant defined set points for heating/cooling/ventilation). Furthermore, the hybrid particle swarm optimisation with sequential quadratic programming training algorithms are used (for the first time to the best of the authors' knowledge) for training the RNN and results show that this algorithm outperforms the widely used gradient descent algorithm for RNN. The results show that occupancy estimation by smart controller is 83.08% accurate.

关键词： neurocontrollers intelligent control building management systems HVAC indoor environment ergonomics gradient methods quadratic programming particle swarm optimisation wireless sensor networks energy conservation occupancy estimation gradient descent algorithm sequential quadratic programming training algorithms hybrid particle swarm optimisation indoor environment predicted mean vote-based set points thermal comfort mode HVAC duct wireless sensor nodes heating-ventilation-air conditioning model predictive controllers artificial neural networks RNN-based controller comfortable environment building energy control system environmental conditions energy usage monitoring energy usage analysis single zone test chamber random neural network smart controller experimental testing

来源：评论

学校读者我要写书评

暂无评论

Blind channel identification using higher-order statistics

引用

JOURNAL OF STATISTICAL COMPUTATION AND SIMULATION 2008年第4期78卷 325-338页

作者： Boulouird, M. Hassani, M. M. Zeroual, A. Cadi Ayyad Univ Fac Sci Semlalia Dept Phys Elect & Instrumentat Lab Marrakech 40001 Morocco

This article addresses the problem of blind identification of a non-minimum phase system from only third- and fourth-order cumulants of the output noisy observations of the system. Nonlinear optimization algorithms, namely the gradient descent, the Gauss-Newton and the Newton-Raphson algorithms, are proposed for estimating the parameters of the moving average models. A relationship between third- and fourth-order cumulants of the noisy system output and the parameters of the model is exploited to build a set of non-linear equations that is solved by means of the three non-linear optimization algorithms cited above. Simulation results demonstrate the performance of the proposed algorithms.

关键词： blind identification higher-order statistics parameter estimation linear algebra solution gradient descent algorithm Gauss-Newton algorithm Newton-Raphson algorithm cumulants

来源：评论

学校读者我要写书评

暂无评论

A comparative study of neuro fuzzy and recurrent neuro fuzzy model-based controllers for real-time industrial processes

引用

SYSTEMS SCIENCE & CONTROL ENGINEERING 2015年第1期3卷 412-426页

作者： Subathra, B. Seshadhri, S. Radhakrishnan, T. K. Kalasalingam Univ ICE Dept Madurai Tamil Nadu India Kalasalingam Univ Int Res Ctr Madurai Tamil Nadu India Natl Inst Technol Tiruchirappalli Tamil Nadu India

Nonlinearities in system dynamics and the multivariable nature of processes offer a stiff challenge in designing predictive controllers that improve process performance in industries. This investigation presents a recurrent neuro fuzzy network (RNFN) model for a nonlinear multivariable system in process industries and a methodology to design model-predictive controllers (MPCs) using the proposed model. The RNFN model combines the learning features of artificial neural networks with human cognition capabilities of fuzzy systems. Therefore, RNFN leads to a modelling framework that has the ability not only to learn the model parameters, but also makes decision on operating region of the nonlinear model depending on the input-output data. Furthermore, the recurrent structure and the introduction of a memory unit between the fuzzy inference and fuzzification layer enhance the prediction capability due to the use of past input-output data, making the model more suitable for designing predictive controllers. Next, the MPC design methodology that exploits the advantages of the RNFN model to optimize the control moves is presented. The proposed MPC uses the gradient descent algorithm to minimize the control moves as against the traditional state-space approaches that require complex computations and solvers. Therefore, implementing the proposed MPC in embedded hardware becomes easier. The proposed modelling framework and the MPC design methodology are illustrated using experiments on a laboratory-scale quadruple tank. Our experiments show that the proposed RNFN-based MPC performs better than the neuro fuzzy network-based MPC for both servo and regulatory responses.

关键词： modelling intelligent techniques hybrid soft computing recurrent neuro fuzzy network MPC gradient descent algorithm

来源：评论

学校读者我要写书评

暂无评论

A fuzzy neighborhood-based training algorithm for feedforward neural networks

引用

NEURAL COMPUTING & APPLICATIONS 2009年第2期18卷 127-133页

作者： Ben Nasr, Mounir Chtourou, Mohamed ENIS Res Unit Intelligent Control Design & Optimizat C Dept Elect Engn Sfax 3038 Tunisia

In this work we present a new hybrid algorithm for feedforward neural networks, which combines unsupervised and supervised learning. In this approach, we use a Kohonen algorithm with a fuzzy neighborhood for training the weights of the hidden layers and gradient descent method for training the weights of the output layer. The goal of this method is to assist the existing variable learning rate algorithms. Simulation results show the effectiveness of the proposed algorithm compared with other well-known learning methods.

关键词： Feedforward neural network gradient descent algorithm Supervised and unsupervised learning Fuzzy self-organizing feature map Hybrid training

来源：评论

学校读者我要写书评

暂无评论

A self-supervised learning system for pattern recognition by sensory integration

引用

NEURAL NETWORKS 1999年第10期12卷 1347-1358页

作者： Yamauchi, K Oota, M Ishii, N Nagoya Inst Technol Dept Intelligence & Comp Sci Showa Ku Nagoya Aichi 466 Japan

Artificial neural networks are useful tools for pattern recognition because they realize nonlinear mapping between input and output spaces. This ability is tuned by supervised learning methods such as back-propagation. In the supervised learning methods, desired outputs of the neural network are needed. However, the desired outputs are usually unknown in unpredictable environments. To solve this problem, this paper presents a self-supervised learning system for category detection. This system learns categories of objects automatically by integrating information from several sensors. We assume that these sensory inputs are always ambiguous patterns that include some noises according to deformations of the objects. After the learning, the system recognizes objects, also controlling the priority of each sensor, according to the deformation of the sensory input pattern. In the simulation, the system is applied to several learning and recognition tasks using artificial or actual sensory inputs. In all tasks, the system found the categories. Particularly, we applied the new system to the learning of five Japanese vowels with the corresponding shapes of the mouth. As result, the system became to yield specific outputs corresponding to each vowel. (C) 1999 Elsevier Science Ltd. All rights reserved.

关键词： self-supervised learning sensory fusion sensory integration gradient descent algorithm

来源：评论

学校读者我要写书评

暂无评论

A new convolutive source separation approach for independent/dependent source components

引用

DIGITAL SIGNAL PROCESSING 2020年 100卷 102701-000页

作者： Mamouni, N. Keziou, A. Fenniri, H. Ghazdali, A. Hakim, A. Univ Reims LMR UMR 9008 CNRS Reims France Univ Reims CReSTIC Reims France Univ Sultan Moulay Slimane ENSA Khouribga LIPIM Beni Mellal Morocco Univ Cadi Ayyad FST LAMAI Marrakech Morocco

In this paper, a new source separation approach, for linear convolutive mixtures of independent/dependent source components, is presented. It consists in minimizing an appropriate separation criterion, measuring the difference between the nonparametric copula density of the estimated sources and semiparametric copula densities modeling the dependency structure of the source components. The proposed approach represents an efficient tool for separating linear convolutive mixtures, especially, when the source components are statistically dependent, if prior information about the dependency structure of the source components is available. (C) 2020 Elsevier Inc. All rights reserved.

关键词： Convolutive source separation Dependent source components Kullback-Leibler divergence between copula densities Copula model selection Statistical estimation gradient descent algorithm

来源：评论

学校读者我要写书评

暂无评论

Riemannian Newton and trust-region algorithms for analytic rotation in exploratory factor analysis

引用

BRITISH JOURNAL OF MATHEMATICAL & STATISTICAL PSYCHOLOGY 2021年第1期74卷 139-163页

作者： Liu, Yang Univ Maryland Dept Human Dev & Quantitat Methodol 12308 Benjamin Bldg3942 Campus Dr College Pk MD 20742 USA

In exploratory factor analysis, latent factors and factor loadings are seldom interpretable until analytic rotation is performed. Typically, the rotation problem is solved by numerically searching for an element in the manifold of orthogonal or oblique rotation matrices such that the rotated factor loadings minimize a pre-specified complexity function. The widely used gradient projection (GP) algorithm, although simple to program and able to deal with both orthogonal and oblique rotation, is found to suffer from slow convergence when the number of manifest variables and/or the number of latent factors is large. The present work examines the effectiveness of two Riemannian second-order algorithms, which respectively generalize the well-established truncated Newton and trust-region strategies for unconstrained optimization in Euclidean spaces, in solving the rotation problem. When approaching a local minimum, the second-order algorithms usually converge superlinearly or even quadratically, better than first-order algorithms that only converge linearly. It is further observed in Monte Carlo studies that, compared to the GP algorithm, the Riemannian truncated Newton and trust-region algorithms require not only much fewer iterations but also much less processing time to meet the same convergence criterion, especially in the case of oblique rotation.

关键词： exploratory factor analysis analytic rotation Riemannian optimization matrix manifold truncated Newton algorithm trust-region algorithm conjugate gradient algorithm gradient projection algorithm gradient descent algorithm

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：