检索结果-内蒙古大学图书馆

Oriented stochastic loss descent algorithm to train very deep multi-layer neural networks without vanishing gradients

引用

KNOWLEDGE-BASED SYSTEMS 2021年 230卷 107391-107391页

作者： Abuqaddom, Inas Mahafzah, Basel A. Faris, Hossam Univ Jordan King Abdullah II Sch Informat Technol Dept Comp Sci Amman Jordan Al Hussien Tech Univ Sch Comp & Informat Amman Jordan Univ Jordan King Abdullah II Sch Informat Technol Dept Informat Technol Amman Jordan

Deep multi-layer neural networks represent hypotheses of very high degree polynomials to solve very complex problems. gradient descent optimization algorithms are utilized to train such deep networks through backpropagation, which suffers from permanent problems such as the vanishing gradient problem. To overcome the vanishing problem, we introduce a new anti-vanishing back-propagated learning algorithm called oriented stochastic loss descent (OSLD). OSLD updates a random-initialized parameter iteratively in the opposite direction of its partial derivative sign by a small positive random number, which is scaled by a tuned ratio of the model loss. This paper compares OSLD to stochastic gradient descent algorithm as the basic backpropagation algorithm and Adam as one of the best backpropagation algorithms in five benchmark models. Experimental results show that OSLD is very competitive to Adam in small and moderate depth models, and OSLD outperforms Adam in very long models. Moreover, OSLD is compatible with current backpropagation architectures except for learning rates. Finally, OSLD is stable and opens more choices in front of the very deep multi-layer neural networks. (C) 2021 Elsevier B.V. All rights reserved.

关键词： Vanishing gradient problem Deep learning Backpropagation gradient descent algorithm Optimization algorithm Deep multi-layer neural network

来源：评论

学校读者我要写书评

暂无评论

ADAPTIVE FUZZY CONTROL FOR ROBOT ARM MANIPULATOR WITH 5-DOF

引用

Transactions of Nanjing University of Aeronautics and Astronautics 2007年第1期24卷 43-47页

作者： Farooq M 王道波南京航空航天大学自动化学院

To control the robot and track the designed trajectory with uncertain disturbances in a specified precision range, an adaptive fuzzy control scheme for the robot arm manipulator is discussed. The controller output error method （COEM） is used to design the adaptive fuzzy controller. A few or all of the parameters of the controller are adjusted by using the gradient descent algorithm to minimize the output error. COEM is adopted in the adaptive control system for the robot arm manipulator with 5-DOF. Simulation results show the effectiveness of the method and the real time adjustment of the parameters.

关键词： robotic arm manipulator adaptive fuzzy control controller output error method (COEM) gradient descent algorithm

来源：评论

学校读者我要写书评

暂无评论

A Performance Study of Random Neural Network as Supervised Learning Tool Using CUDA

引用

JOURNAL OF INTERNET TECHNOLOGY 2016年第4期17卷 771-778页

作者： Basterrech, Sebastian Janousek, Jan Snasel, Vaclav VSB Tech Univ Ostrava Fac Elect Engn & Comp Sci Dept Comp Sci Ostrava Czech Republic

The Graphics Processing Units (GPUs) have been used for accelerating graphic calculations as well as for developing more general devices. One of the most used parallel platforms is the Compute Unified Device Architecture (CUDA), which allows implementing in parallel multiple GPUs obtaining a high computational performance. Over the last years, CUDA has been used for the implementation of several parallel distributed systems. At the end of the 80s, it was introduced a type of Neural Networks (NNs) inspired of the behavior of queueing networks named Random Neural Networks (RNN). The method has been successfully used in the Machine Learning community for solving many learning benchmark problems. In this paper, we implement in CUDA the gradient descent algorithm for optimizing a RNN model. We evaluate the performance of the algorithm on two real benchmark problems about energy sources. In addition, we present a comparison between the parallel implement in CUDA and the traditional implementation in C programming language.

关键词： Random neural network Parallel computing CUDA gradient descent algorithm

来源：评论

学校读者我要写书评

暂无评论

New semi-analytical solutions of the time-fractional Fokker-Planck equation by the neural network method

引用

OPTIK 2022年 259卷

作者： Wei, Jia-Li Wu, Guo-Cheng Liu, Bao-Qing Zhao, Zhengang Nanjing Univ Finance & Econ Sch Appl Math Nanjing 210023 Jiangsu Peoples R China Neijiang Normal Univ Coll Math & Informat Sci Data Recovery Key Lab Sichuan Prov Neijiang 641100 Peoples R China Shanghai Customs Coll Dept Fundamental Courses Shanghai 201204 Peoples R China

This paper suggests a neural network method for solving the time-fractional Fokker-Planck equation. An energy function is constructed by means of initial-boundary value conditions. The Caputo derivative is approximated by L-1 numerical scheme and an unconstrained discretization minimization problem is presented. gradient descent algorithm is adopted for neural network training. Semi-analytical solutions are obtained where two numerical examples demonstrate the method's efficiency.

关键词： Fractional Fokker-Planck equation L-1 numerical scheme Neural network gradient descent algorithm

来源：评论

学校读者我要写书评

暂无评论

Mixed-integer nonlinear programming model for layout design of subsea satellite well system in deep water oil field

引用

AUTOMATION IN CONSTRUCTION 2021年 123卷 103524-103524页

作者： Hong, Cheng Estefen, Segen F. Wang, Yuxi Lourenco, Marcelo Igor Ningbo Univ Fac Maritime & Transportat Ningbo 315211 Peoples R China Univ Fed Rio de Janeiro Ocean Engn Dept COPPE BR-21941972 Rio De Janeiro Brazil State Key Lab Petr Pollut Control Beijing 102206 Peoples R China CNPC Res Inst Safety & Environm Technol Beijing 102206 Peoples R China

This paper focuses on the concept of a subsea satellite well system in deep water oil field, and a mixed-integer nonlinear programming model (MINLP) is proposed to help design the layout to minimize the payback period. The proposed model has two key aspects. First, the objective function, payback period, reflects the link between the total cost and production. And second, the Floating Production Storage and Offloading units (FPSOs), subsea wells, flowlines, and subsea obstacles are integrated for the modeling, presenting the interaction of the components from underground to the sea level. A decomposition strategy based on gradient descent algorithm is proposed to solve the model. The case studies indicate the model's feasibility. Besides, two different applications of the model are presented, one is to optimize the layout under given horizontal displacements and the other is the cost comparison between drilling horizontal well and vertical well, indicating the model's flexibility.

关键词： Subsea production system Satellite well system concept Layout design Mixed-integer nonlinear programming gradient descent algorithm

来源：评论

学校读者我要写书评

暂无评论

Learning-Based Motion Planning of a 14-DOF Biped Robot on 3D Uneven Terrain Containing a Ditch

引用

INTERNATIONAL JOURNAL OF HUMANOID ROBOTICS 2021年第6期18卷

作者： Kumar, Jitendra Dutta, Ashish IIT Kanpur Dept Mech Engn Kanpur 208016 Uttar Pradesh India

In this paper, a new method is proposed that integrates the 3D terrain information, ditch geometry, and biped dynamics for motion planning of a 14-DOF biped robot on 3D terrain containing a 3D ditch. The path planning is modeled as a wavefront propagation in Non-uniform medium represented by the Eikonal equation. A speed function expresses the inhomogeneity of uneven terrain. The Eikonal equation is solved by the Fast marching method (FMM) to obtain the global path. Ten Footstep variables (FSVs) characterize one step of walk on a 3D uneven terrain surface. The hip and foot trajectory parameters (HFTPs) are used to construct cubic spline-based hip and foot trajectories of the biped robot. The optimal value of HFTPs is obtained by a Genetic algorithm by minimization of energy and satisfying the constraint of dynamic balance. A walk-dataset is created that contains the optimal trajectories for different FSVs. The generated walk-dataset was used to train the biped to walk on rough terrain using a feed-forward Neural network for making a real-time estimate of optimal HFTPs. Simulation results validate the effectiveness of the proposed method of ditch crossing on different uneven terrains.

关键词： Fast marching method gradient descent algorithm genetic algorithm footstep variables hip and foot trajectory parameters walk-dataset

来源：评论

学校读者我要写书评

暂无评论

A hybrid metaheuristic algorithm for location inventory routing problem with time windows and fuel consumption

引用

EXPERT SYSTEMS WITH APPLICATIONS 2021年 166卷 114034-114034页

作者： Wu, Weitiao Zhou, Wei Lin, Yue Xie, Yuanqi Jin, Wenzhou South China Univ Technol Sch Civil Engn & Transportat Guangzhou 510641 Peoples R China

We introduce a multi-period location-inventory-routing problem with time windows and fuel consumption, which simultaneously optimizes the location, routing, and inventory decisions for both the distribution center and customers in a multi-echelon supply chain. To better reflect reality, the fuel consumption is also incorporated into the variable transportation cost. The problem is formulated as a mixed integer nonlinear programming model. We then propose a two-stage hybrid metaheuristic algorithm to address this problem. In the first stage, a customized genetic algorithm is proposed. In the second stage, a gradient descent algorithm is used to improve the inventory decision to further reduce the total cost. Results of numerical experimentations on generated instances confirm the effectiveness of the algorithm. Results show that inventory management activities contribute considerably to total cost saving. Given the cost trade-off between transportation and inventory, the retailers' inventory level shows more shortages after post-optimization, while the inventory level in the distribution centers can be either reduced or increased, depending on the spatial distribution of retailers in the vicinity of the distribution center. Sensitivity analysis on the model parameters is also conducted to provide managerial insights.

关键词： Location-inventory-routing problem Fuel consumption Hybrid heuristic algorithm gradient descent algorithm

来源：评论

学校读者我要写书评

暂无评论

Extended Content-boosted Matrix Factorization algorithm for Recommender Systems

引用

Procedia Computer Science 2014年 35卷 417-426页

作者： Oleksandr Krasnoshchok Yngve Lamo Bergen University College Nygrdsgaten 112 Bergen 5020 Norway

Recommender technologies have been developed to give helpful predictions for decision making under uncertainty. An extensive amount of research has been done to increase the quality of such predictions, currently the methods based on matrix factorization are recognized as one of the most efficient. The focus of this paper is to extend a matrix factorization algorithm with content awareness to increase prediction accuracy. A recommender system prototype based on the resulting Extended Content-Boosted Matrix Factorization algorithm is designed, developed and evaluated. The algorithm has been evaluated by empirical evaluation, which starts with creating of an experimental design, then conducting off-line empirical tests with accuracy measurement. The result revealed further potential of the content awareness in matrix factorization methods, which has not been fully realized in the generalized alignment-biased algorithm by Nguyen and Zhu and uncovers opportunities for future research.

关键词： Recommender System Matrix Factorization Content-Boosted Matrix Factorization Extended Content-Boosted Matrix Factorization gradient descent algorithm Content Aware Collaborative Filtering algorithm

来源：评论

学校读者我要写书评

暂无评论

algorithm of Video Semantic Classification Based on IAGA and Deep Convolution Neural Network

引用

电脑学刊 2018年第5期29卷 52-65页

作者： Min Wang Ke-Xin Liu Ming-Fei Wei Li-Cai Zhang

The rise of convolutional neural network (CNN) has greatly improved the disadvantage of the traditional video classification method. However, in the pre-training process of classification network, often due to over-fitting, gradient disappearance and other factors lead to training data convergence performance is poor, thus would affect the accuracy of the classifier. Aiming at the problem of network optimization, this paper proposes an algorithm to combine improved adaptive genetic algorithm (IAGA) with deep convolution neural network (DCNN) classifier. The weighting of the network is initialized by the IAGA algorithm, and the weight is corrected by combining the gradient descent (GD) algorithm. Finally, the fusion of global feature extracted by the network is input into the extreme learning machine (ELM) for classification. The results of the news video classification show that the algorithm can combine the global search ability of IAGA with the local optimization ability of gradient descent algorithm to improve the accuracy of the training network with less parameters, and the average classification accuracy rate can reach 90.03%. Compared with the three existing algorithms, the algorithm has higher classification accuracy. Compared with the four kinds of network pre-training methods, the algorithm presented in this article is more dominant.

关键词： deep convolutional neural network extreme learning machine gradient descent algorithm improved adaptive genetic algorithm video semantic classification

来源：评论

学校读者我要写书评

暂无评论

Cascaded Internal Phase Control of All-Fiber Coherent Fiber Laser Array

引用

FRONTIERS IN PHYSICS 2022年 10卷

作者： Chang, Hongxiang Su, Rongtao Zhang, Yuqiu Jiang, Min Chang, Qi Long, Jinhu Ma, Pengfei Ma, Yanxing Zhou, Pu Natl Univ Def Technol Coll Adv Interdisciplinary Studies Changsha Peoples R China

Fiber lasers have been widely used in medical care, industries, and scientific research in recent years. The coherent beam combining of fiber lasers with an internal phase control has drawn many interests at present, which is a promising method to achieve a large-scale optical phased array. In this article, we presented a cascaded internal phase control method to expand the internal all-fiber phased array. The method distributes the phase measurements to a series of internal Mach-Zender interferometers. Then, the phase of each loop is locked by the gradient descent algorithm. The electric control method to compensate pi-ambiguity between channels is proposed. Finally, the phases of the three fiber beams are locked experimentally to verify the feasibility of the method, and the residue phase error is better than lambda/22.

关键词： coherent beam combining internal phase-locking fiber laser array gradient descent algorithm laser field manipulation

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：