检索结果-内蒙古大学图书馆

OPTIMUM GUARD ZONE FOR SELF-SUPERVISED learning

IEE PROCEEDINGS-E COMPUTERS AND DIGITAL TECHNIQUES 1982年第1期129卷 9-14页

作者： PAL, SK Electrical Engineering Department Imperial College of Science and Technology London UK

A self-supervised learning algorithm using fuzzy set and the concept of guard zones around the class representative vectors is presented and demonstrated for vowel recognition. An optimum guard zone having the best match with the fully supervised performance is determined. Results are also compared with that of nonsupervised case for various orders of input patterns.

关键词： Combinatorial mathematics vowel recognition fuzzy set theory pattern recognition class representative vectors Optical information, image and video signal processing Pattern recognition learning algorithm self supervised learning fuzzy set guard zone concept

来源：评论

学校读者我要写书评

暂无评论

Modulated Hebb-Oja learning rule - A method for principal subspace analysis

引用

IEEE TRANSACTIONS ON NEURAL NETWORKS 2006年第2期17卷 345-356页

作者： Jankovic, MV Ogawa, H Elect Engn Inst Nikola Tesla Belgrade 11000 Serbia Monteneg Tokyo Inst Technol Tokyo 1528552 Japan

This paper presents analysis of the recently proposed modulated Hebb-Oja (MHO) method that performs linear mapping to a lower-dimensional subspace. Principal component subspace is the method that will be analyzed. Comparing to some other well-known methods for yielding principal component subspace (e.g., Oja's Subspace learning algorithm), the proposed method has one feature that could be seen as desirable from the biological point of view-synaptic efficacy learning rule does not need the explicit information about the value of the other efficacies to make individual efficacy modification. Also, the simplicity of the "neural circuits" that perform global computations and a fact that their number does not depend on the number of input and output neurons, could be seen as good features of the proposed method.

关键词： learning algorithm neural networks principal component analysis (PCA) principal subspace analysis (PSA)

来源：评论

学校读者我要写书评

暂无评论

Acceleration of the back propagation through dynamic adaptation of the learning rate

引用

INTERNATIONAL JOURNAL OF COMPUTER MATHEMATICS 1997年第1-2期65卷 1-17页

作者： Zainuddin, Z Evans, DJ Univ Sains Malaysia Sch Math Sci Penang 11800 Malaysia Loughborough Univ Technol Parallel Algorithms Res Ctr Loughborough LE11 3TU Leics England

Standard backpropagation, as with many gradient based optimization methods converges slowly as neural networks training problems become larger and more complex. In this paper, we present a new algorithm, dynamic adaptation of the learning rate to accelerate steepest descent. The underlying idea is to partition the iteration number domain into n intervals and a suitable value for the learning rate is assigned for each respective iteration interval. We present a derivation of the new algorithm and test the algorithm on several classification problems. As compared to standard backpropagation, the convergence rate can be improved immensely with only a minimal increase in the complexity of each iteration.

关键词： backpropagation steepest descent learning algorithm convergence

来源：评论

学校读者我要写书评

暂无评论

A REGULARIZATION METHOD FOR NEURAL-NETWORK learning THAT MINIMIZES ESTIMATION ERROR

引用

IEICE TRANSACTIONS ON INFORMATION AND SYSTEMS 1994年第4期E77D卷 418-424页

作者： YAMADA, M Toshiba Corp Kawasaki-shi Japan

A new regularization cost function for generalization in real-valued function learning is proposed. This cost function is derived from the maximum likelihood method using a modified sample distribution, and consists of a sum of square errors and a stabilizer which is a function of integrated square derivatives. Each of the regularization parameters which gives the minimum estimation error can be obtained uniquely and non-empirically. The parameters are not constants and change in value during learning. Numerical simulation shows that this cost function predicts the true error accurately and is effective in neural network learning.

关键词： NEUROCOMPUTING learning algorithm learning THEORY

来源：评论

学校读者我要写书评

暂无评论

Automated fault diagnosis in nonlinear multivariable systems using a learning methodology

引用

IEEE TRANSACTIONS ON NEURAL NETWORKS 2000年第1期11卷 91-101页

作者： Trunov, AB Polycarpou, MM Univ Cincinnati Dept Elect & Comp Engn & Comp Sci Cincinnati OH 45221 USA

The paper presents a robust fault diagnosis scheme for detecting and approximating state and output faults occurring in a class of nonlinear multiinput-multioutput dynamical systems, Changes in the system dynamics due to a fault are modeled as nonlinear functions of the control input and measured output variables, Both state and output faults can be modeled as slowly developing (incipient) or abrupt, with each component of the state/output fault vector being represented by a separate time profile. The robust fault diagnosis scheme utilizes on-line approximators and adaptive nonlinear filtering techniques to obtain estimates of the fault functions. Robustness with respect to modeling uncertainties, fault sensitivity and stability properties of the learning scheme are rigorously derived and the theoretical results are illustrated by a simulation example of a fourth-order satellite model.

关键词： adaptive law fault detection fault diagnosis learning algorithm neural network nonlinear estimator on-line approximator sensor fault state fault

来源：评论

学校读者我要写书评

暂无评论

Output feedback reinforcement learning based optimal output synchronisation of heterogeneous discrete-time multi-agent systems

引用

IET CONTROL THEORY AND APPLICATIONS 2019年第17期13卷 2866-2876页

作者： Rizvi, Syed Ali Asad Lin, Zongli Univ Virginia Charles L Brown Dept Elect & Comp Engn Charlottesville VA 22904 USA

This study proposes a model-free distributed output feedback control scheme that achieves synchronisation of the outputs of the heterogeneous follower agents with that of the leader agent in a directed network. A distributed two degree of freedom approach is presented that separates the learning of the optimal output feedback and the feedforward terms of the local control law for each agent. The local feedback parameters are learned using the proposed off-policy Q-learning algorithm, whereas a gradient adaptive law is presented to learn the local feedforward control parameters to achieve asymptotic tracking of each agent. This learning scheme and the resulting distributed control laws neither require access to the local internal state of the agents nor do they need an additional distributed leader state observer. The proposed approach has the advantage over the previous state augmentation approaches as it circumvents the need of introducing a discounting factor in the local performance functions. It is shown that the proposed algorithm converges to the optimal solution of the algebraic Riccati equation and the output regulator equations without explicitly solving them as long as the leader agent is reachable directly or indirectly from all the follower agents. Simulation results validate the proposed scheme.

关键词： synchronisation distributed control learning (artificial intelligence) feedback multi-agent systems adaptive control Riccati equations discrete time systems control system synthesis feedforward observers closed loop systems optimal control control system analysis computing local feedback parameters learning algorithm gradient adaptive law local feedforward control parameters learning scheme resulting distributed control laws local internal state local performance functions optimal solution output regulator equations leader agent output feedback reinforcement learning optimal output synchronisation discrete-time multiagent systems model-free distributed output feedback control scheme heterogeneous follower agents directed network freedom approach optimal output feedback feedforward terms local control law distributed two degree of freedom approach state augmentation approaches distributed leader state observer

来源：评论

学校读者我要写书评

暂无评论

Decentralized learning multi-agent system for online machine shop scheduling problem

引用

JOURNAL OF MANUFACTURING SYSTEMS 2023年 67卷 338-360页

作者： Didden, Jeroen B. H. C. Dang, Quang-Vinh Adan, Ivo J. B. F. Eindhoven Univ Technol Dept Ind Engn & Innovat Sci POB 513 NL-5600 MB Eindhoven Netherlands

Customer profiles have rapidly changed over the past few years, with products being requested with more customization and with lower demand. In addition to the advances in technologies owing to Industry 4.0, manufacturers explore autonomous and smart factories. This paper proposes a decentralized multi-agent system (MAS), including intelligent agents that can respond to their environment autonomously through learning capabilities, to cope with an online machine shop scheduling problem. In the proposed system, agents participate in auctions to receive jobs to process, learn how to bid for jobs correctly, and decide when to start processing a job. The objective is to minimize the mean weighted tardiness of all jobs. In contrast to the existing literature, the proposed MAS is assessed on its learning capabilities, producing novel insights concerning what is relevant for learning, when re-learning is needed, and system response to dynamic events (such as rush jobs, increase in processing time, and machine unavailability). Computational experiments also reveal the outperformance of the proposed MAS to other multi-agent systems by at least 25% and common dispatching rules in mean weighted tardiness, as well as other performance measures.

关键词： Multi-agent system Decentralized systems learning algorithm Industry 4 0 Smart manufacturing

来源：评论

学校读者我要写书评

暂无评论

learning-based force servoing control of a robot with vision in an unknown environment

引用

Journal of Systems Engineering and Electronics 2004年第2期15卷 171-178页

作者： XiaoNanfeng SchoolofComputerScienceandEngineering SouthChinaUniversityofTechnologyGuangzhou510641P.R.China

A learning-based control approach is presented for force servoing of a robot with vision in an unknown environment. Firstly, mapping relationships between image features of the servoing object and the joint angles of the robot are derived and learned by a neural network. Secondly, a learning controller based on the neural network is designed for the robot to trace the object. Thirdly, a discrete time impedance control law is obtained for the force servoing of the robot, the on-line learning algorithms for three neural networks are developed to adjust the impedance parameters of the robot in the unknown environment. Lastly, wiping experiments are carried out by using a 6 DOF industrial robot with a CCD camera and a force/torque sensor in its end effector, and the experimental results confirm the effecti veness of the approach.

关键词： robotics force servoing vision control learning algorithm neural network.

来源：评论

学校读者我要写书评

暂无评论

MECHANICAL SYSTEM MODELING USING RECURRENT NEURAL NETWORKS VIA QUASI-NEWTON learning-METHODS

引用

APPLIED MATHEMATICAL MODELLING 1995年第7期19卷 421-428页

作者： LI, CJ YAN, LL RENSSELAER POLYTECH INST DEPT MECH ENGN AERONAUT ENGN & MECHTROYNY 12180 COLUMBIA UNIV DEPT MECH ENGNNEW YORKNY 10027

This paper describes a set of efficient learning algorithms for recurrent neural networks (RNN) to facilitate the nonlinear modelling of mechanical systems. These learning algorithms are based on the quasi-Newton methods that estimate the inverse Hessian of an objective function from the gradient to enable Newton-like optimization algorithms. The simulation results with two Boolean functions indicate that the new algorithms based on the classical quasi-Newton methods are about two orders of magnitude faster than the steepest descent method. Furthermore, the learning algorithms based on the quasi-Newton with initial scaling and self-scaling are even more efficient than the classical quasi-Newton methods. For instance, the self-scaling method is three orders of magnitude faster than the steepest descent method. To validate the usefulness of the RNNs in nonlinear mechanical system modelling, RNNs are trained to emulate the step response of a robot arm and identify an adequate model of a 20 HP screw compressor from its operating data.

关键词： RECURRENT NEURAL NETWORKS learning algorithm QUASI-NEWTON OPTIMIZATION TECHNIQUE NONLINEAR SYSTEM MODELING

来源：评论

学校读者我要写书评

暂无评论

learning and Convergence of Fuzzy Cognitive Maps Used in Pattern Recognition

引用

NEURAL PROCESSING LETTERS 2017年第2期45卷 431-444页

作者： Napoles, Gonzalo Papageorgiou, Elpiniki Bello, Rafael Vanhoof, Koen Hasselt Univ Fac Business Econ Hasselt Belgium Cent Univ Las Villas Dept Comp Sci Santa Clara Cuba Technol Educ Inst Cent Greece Dept Comp Engn Lamia Greece

In recent years fuzzy cognitive maps (FCM) have become an active research field due to their capability for modeling complex systems. These recurrent neural models propagate an activation vector over the causal network until the map converges to a fixed-point or a maximal number of cycles is reached. The first scenario suggests that the FCM converged, whereas the second one implies that cyclic or chaotic patterns may be produced. The non-stable configurations are mostly related with the weight matrix that defines the causal relations among concepts. Such weights could be provided by experts or automatically computed from historical data by using a learning algorithm. Nevertheless, from the best of our knowledge, population-based algorithms for FCM-based systems do not include the map convergence into their learning scheme and thus, non-stable configurations could be produced. In this research we introduce a population-based learning algorithm with convergence features for FCM-based systems used in pattern classification. This proposal is based on a heuristic procedure, called Stability based on Sigmoid Functions, which allows improving the convergence of sigmoid FCM used in pattern classification. Numerical simulations using six FCM-based classifiers have shown that the proposed learning algorithm is capable of computing accurate parameters with improved convergence features.

关键词： Fuzzy cognitive maps learning algorithm Convergence

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：