检索结果-内蒙古大学图书馆

Time-oriented hierarchical method for computation of principal components using subspace learning algorithm.

International journal of neural systems 2004年第5期14卷 313-323页

作者： Jankovic, Marko Ogawa, Hidemitsu Control Department Electrical Engineering Institute Nikola Tesla Koste Glavinica 8a Belgrade 11000

Principal Component Analysis (PCA) and Principal Subspace Analysis (PSA) are classic techniques in statistical data analysis, feature extraction and data compression. Given a set of multivariate measurements, PCA and PSA provide a smaller set of "basis vectors" with less redundancy, and a subspace spanned by them, respectively. Artificial neurons and neural networks have been shown to perform PSA and PCA when gradient ascent (descent) learning rules are used, which is related to the constrained maximization (minimization) of statistical objective functions. Due to their low complexity, such algorithms and their implementation in neural networks are potentially useful in cases of tracking slow changes of correlations in the input data or in updating eigenvectors with new samples. In this paper we propose PCA learning algorithm that is fully homogeneous with respect to neurons. The algorithm is obtained by modification of one of the most famous PSA learning algorithms--Subspace learning algorithm (SLA). Modification of the algorithm is based on Time-Oriented Hierarchical Method (TOHM). The method uses two distinct time scales. On a faster time scale PSA algorithm is responsible for the "behavior" of all output neurons. On a slower scale, output neurons will compete for fulfillment of their "own interests". On this scale, basis vectors in the principal subspace are rotated toward the principal eigenvectors. At the end of the paper it will be briefly analyzed how (or why) time-oriented hierarchical method can be used for transformation of any of the existing neural network PSA method, into PCA method.

关键词： Feature extraction learning algorithm neural networks time hierarchy

来源：评论

学校读者我要写书评

暂无评论

Multiresolution Process Neural Network and Its learning algorithm 4

Multiresolution Process Neural Network and Its Learning Algo...

引用

4th International Conference on Systems and Informatics (ICSAI)

作者： Li, Yang An, Yi Yu, Ning Zhu, Rui-bo State Grid Informat & Telecommun Co SEPC 71 Fu Dong St Taiyuan 030001 Shanxi Peoples R China

ISBN: (纸本)9781538611074

A new model of multiresolution process neural network (MRPNN) which incorporates the characteristics of hierarchical, multiresolution and local learning capability is proposed based on the multiresolution analysis theory and process neural network model. This type of neural network facilitates in tackling with continuous input signals, which makes it possible to forecast time series problem. In addition, in order to approximate the nonlinear system, the hidden layer is used to deal with the nonlinear and complexity problems. A novel learning algorithm is given to expand the input functions and network weight functions based on the expansion of the orthogonal basis functions, subsequently The learning algorithm then builds the network by locating high error regions and adding nodes that get its activation function from the higher resolution space of the current local node, and its support falls within the high error region. Finally, the network is used to forecast the medium-term load of power system. Simulation results show that the network has good convergence and high accuracy. This method provides an effective solution to medium-term load forecasting in power system.

关键词： Process neuron Multiresolution process neural network (MRPNN) learning algorithm Power load forecasting

来源：评论

学校读者我要写书评

暂无评论

Arm exoskeleton for rehabilitation following stroke by learning algorithm prediction

Arm exoskeleton for rehabilitation following stroke by learn...

引用

International Symposium on Medical and Rehabilitation Robotics and Instrumentation (MRRI)

作者： Fikri, Mohd Amiruddin Abdullah, Sukarnur Che Ramli, M. Hanif M. Univ Teknol MARA UiTM Fac Mech Engn Shah Alam 40450 Selangor Malaysia

Stroke is a major cause of disability in worldwide and also one of the causes of death after coronary heart disease. Many devices had been designed for hand motor function rehabilitation that a stroke survivor can use for bilateral movement practice. This paper presents an arm motor function rehabilitation device where it is designed to predict the position angle for the robotic arm. MATLAB software is used for real-time positioning that can be developed by SIMULINK block diagram and proof by the simulator in program code in order for devising to operate under the position demand. All the angular motions or feedback to the simulation mode from the attached optical encoders via the Data Acquisition Card (DAQ). The learning algorithm can directly determine the position of its joint and can therefore completely eliminate the need for any system modelling. The robotic arm shows a successful implementation of the learning algorithm in predicting the behavior for arm exoskeleton. (C) 2014 The Authors. Published by Elsevier B.V.

关键词： arm exoskeleton stroke rehabilitation learning algorithm

来源：评论

学校读者我要写书评

暂无评论

A Simple learning algorithm for Contact-Rich Robotic Grasping

A Simple Learning Algorithm for Contact-Rich Robotic Graspin...

引用

21st International Conference on Global Research and Education (Inter-Academia)

作者： Przybylski, M. Klimaszewski, J. Wildner, K. Warsaw Univ Technol Inst Automat Control & Robot Fac Mechatron Sw A Boboli 8 PL-02525 Warsaw Poland Warsaw Univ Technol Inst Metrol & Biomed Engn Fac Mechatron Sw A Boboli 8 PL-02525 Warsaw Poland

This paper presents the preliminary results of the work on a control algorithm for a two-finger gripper equipped with an electronic skin (e-skin). The e-skin measures the magnitude and location of the pressure applied to it. Contact localization allowed the development of a reliable control algorithm for robotic grasping. The main contribution of this work is the learning algorithm that adjusts the pose of the gripper during the pre-grasp approach step based on contact information. The algorithm was tested on different objects and showed comparable grasping reliability to the vision-based approach. The developed tactile sensor-rich gripper with a dedicated control algorithm may find applications in various fields, from industrial robotics to advanced interactive robots.

关键词： robotic manipulation contact-rich manipulation electronic skin learning algorithm

来源：评论

学校读者我要写书评

暂无评论

Traffic Light Detection: A learning algorithm and Evaluations on Challenging Dataset 18

Traffic Light Detection: A Learning Algorithm and Evaluation...

引用

18th IEEE International Conference on Intelligent Transportation Systems

作者： Philipsen, Mark P. Jensen, Morten B. Mogelmose, Andreas Moeslund, Thomas B. Trivedi, Mohan M. Aalborg Univ Visual Anal People Lab DK-9000 Aalborg Denmark Univ Calif San Diego Comp Vis & Robot Res Lab La Jolla CA 92093 USA

ISBN: (纸本)9781467365963

Traffic light recognition (TLR) is an integral part of any intelligent vehicle, which must function in the existing infrastructure. Pedestrian and sign detection have recently seen great improvements due to the introduction of learning based detectors using integral channel features. A similar push have not yet been seen for the detection sub-problem of TLR, where detection is dominated by methods based on heuristic models. Evaluation of existing systems is currently limited primarily to small local datasets. In order to provide a common basis for comparing future TLR research an extensive public database is collected based on footage from US roads. The database consists of both test and training data, totaling 46,418 frames and 112,971 annotated traffic lights, captured in continuous sequences under a varying light and weather conditions. The learning based detector achieves an AUC of 0.4 and 0.32 for day sequence 1 and 2, respectively, which is more than an order of magnitude better than the two heuristic model-based detectors.

关键词： intelligent transportation systems learning (artificial intelligence) object detection pedestrians road traffic traffic engineering computing TLR US roads integral channel features intelligent vehicle learning algorithm learning based detector pedestrian detection sign detection traffic light detection traffic light recognition Computer vision Databases Detectors Feature extraction Image color analysis Intelligent vehicles Roads

来源：评论

学校读者我要写书评

暂无评论

A novel link structure and learning algorithm of feedforward neural network

A novel link structure and learning algorithm of feedforward...

引用

7th International Conference on Signal Processing

作者： Wu, Y Tongji Univ Dept Comp Sci & Engn Shanghai 200092 Peoples R China

ISBN: (纸本)7121002159

The links from hidden layer to output layer are expanded for improving the learning performance of neural network. Based on this, a new neural network structure is proposed, and a learning algorithm is derived on it. And then, several n-parity, function approximation and pattern classification problem simulations are made to verify the effectiveness of the proposed method. The experimental results show that the proposed method has the dual merits of quick training speed and good generalization capability. It proves to be a very effective method.

关键词： neural network learning algorithm link structure generalization capability

来源：评论

学校读者我要写书评

暂无评论

Implementing a Self-structuring Data learning algorithm

Implementing a Self-structuring Data Learning Algorithm

引用

Conference on Cyber Sensing

作者： Graham, James Carson, Daniel Ternovskiy, Igor Ohio Univ Athens OH 45701 USA Riverside Res Beavercreek OH 45431 USA Air Force Res Lab Sensors Directorate Wright Patterson AFB OH 45324 USA

ISBN: (纸本)9781510600676

In this paper, we elaborate on what we did to implement our self-structuring data learning algorithm. To recap, we are working to develop a data learning algorithm that will eventually be capable of goal driven pattern learning and extrapolation of more complex patterns from less complex ones. At this point we have developed a conceptual framework for the algorithm, but have yet to discuss our actual implementation and the consideration and shortcuts we needed to take to create said implementation. We will elaborate on our initial setup of the algorithm and the scenarios we used to test our early stage algorithm. While we want this to be a general algorithm, it is necessary to start with a simple scenario or two to provide a viable development and testing environment. To that end, our discussion will be geared toward what we include in our initial implementation and why, as well as what concerns we may have. In the future, we expect to be able to apply our algorithm to a more general approach, but to do so within a reasonable time, we needed to pick a place to start.

关键词： learning algorithm autonomous learning algorithm implementation data modeling

来源：评论

学校读者我要写书评

暂无评论

ANEFFICIENT learning algorithm FOR BINARY FEEDFORWARD NEURAL NETWORKS 14

ANEFFICIENT LEARNING ALGORITHM FOR BINARY FEEDFORWARD NEURAL...

引用

International Conference on Machine learning and Cybernetics (ICMLC)

作者： Zhou, Jianxin Zeng, Xiaoqin Chan, Patrick P. K. Hohai Univ Inst Intelligence Sci & Technol Nanjing 211100 Jiangsu Peoples R China S China Univ Technol Sch Comp Sci & Engn Guangzhou 510006 Guangdong Peoples R China

ISBN: (纸本)9781467372206

This paper proposes a novel learning algorithm of Binary Feedforward Neural Networks (BFNNs) by combining the self-adaptations of both architecture and *** to the learning algorithm of Extreme learning Machine (ELM), our algorithm only adapts the number of hidden neurons and output weights to effectively train BFNNs with a single hidden layer for classification problems. The algorithm consists of two steps including the expanding and pruning phases. During the expandingphase, the algorithm increases the hidden neurons and also searches the weight of the output neuronusing the Perceptron learning Rule to increase the learning accuracy. In the pruning phase, the least relevant hidden neurons measured by a proposed binary neuron's sensitivity are pruned to reduce the complexity of the modeland increase the generalization ability. Experimental results confirmed the feasibility and effectiveness of the proposed algorithm.

关键词： Binary feedforward neural network learning algorithm Sensitivity Architecture pruning Classification

来源：评论

学校读者我要写书评

暂无评论

Tracking-learning-Detection Adopted Unsupervised learning algorithm 7

Tracking-Learning-Detection Adopted Unsupervised Learning Al...

引用

Seventh International Conference on Knowledge and Systems Engineering (KSE)

作者： Park, Eunae Ju, Hyuntae Jeong, Yong Mu Min, Soo-Young Korea Elect Technol Inst Software Device Res Ctr Songnam Gyeonggi Do South Korea

ISBN: (纸本)9781467380133

In this paper, we research the real-time object tracking technology. The object tracking algorithm discussed in this paper is developed based on the Tracking-learning-Detection(TLD) and the Centroid Neural Network(CNN). The object is unknown ahead of tracking;the model of the object is composed of objects transformed geometrically immediately after tracking. The TLD framework is useful for long-term object tracking in a video stream because the TLD framework applies a novel learning algorithm called P-N learning. We propose a method that applies the CNN algorithm to the TLD framework. The CNN algorithm is an unsupervised learning algorithm that provides a stable result, regardless of initial values of learning coefficients and neurons. The object tracking algorithm discussed in this paper has a higher accuracy than that of TLD in terms of detection. Additionally, it exhibits better processing performance than that of TLD.

关键词： object tracking learning algorithm real-time system

来源：评论

学校读者我要写书评

暂无评论

A Novel Adaptive Fast learning algorithm for 2DPCA

A Novel Adaptive Fast Learning Algorithm for 2DPCA

引用

International Conference on Information, Communication and Engineering (ICICE 2012)

作者： Chen, Liang-Hwa Chang, Yen-Ching Chang, Po-Lun Chang, Chun-Ming Lunghwa Univ Sci & Technol Dept Comp Informat & Network Engn Tao Yuan Taiwan Lunghwa Univ Sci & Technol Dept Elect Engn Tao Yuan Taiwan Chung Shan Med Univ Dept Med Informat Taichung Taiwan Asia Univ Dept Informat Sci & Applicat Taichung Taiwan

ISBN: (纸本)9783037856727

We propose a novel adaptive fast learning (AFL) algorithm for two-dimensional principal component analysis (2DPCA) in this paper. As opposite to conventional PCA which is based on 1D data vectors, 2DPCA is based on 2D image matrices and thus has higher accuracy than conventional PCA when applied to applications such as face recognition, facial expression recognition, palmprint recognition, etc. Our proposed AFL algorithm simultaneously estimates both eigenvectors and corresponding eigenvalues, and then adaptively sets the learning rate parameters of neurons to ensure all neurons learning with almost the same fast speed. Requiring no image covariance matrix evaluation, the desired multiple eigenvectors of 2DPCA can thus be learned effectively in the form of weight vectors of neurons. The proposed AFL algorithm can also be applied to learning for T-2DPCA. Simulation experiments performed on face database such as the YaleB database clearly demonstrate that the proposed AFL algorithm performs very well and thus is a very effective computational tool for both 2DPCA and T-2DPCA.

关键词： 2DPCA PCA Neural network learning 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：