In this paper. a novel neural network algorithm is proposed, which solve the quadratic programming problem with linear constraints based on Fibonacci method. Compared with the existing models for solving the quadratic...
详细信息
ISBN:
(纸本)9783642132773
In this paper. a novel neural network algorithm is proposed, which solve the quadratic programming problem with linear constraints based on Fibonacci method. Compared with the existing models for solving the quadratic programming problem with linear constraints, it is more universal, since the objective function of the quadratic programming not only can be convex function but also can be quasi convex function. Finally, example is provided to show the applicability of the proposed neural network algorithm.
A pure-strategy, simplified poker (PSP) game is proposed, where two players draw from a small and discrete number of hands. Equilibrium strategies of the game are described and an experiment is conducted where 120 sub...
详细信息
A pure-strategy, simplified poker (PSP) game is proposed, where two players draw from a small and discrete number of hands. Equilibrium strategies of the game are described and an experiment is conducted where 120 subjects played the PSP against a computer, which was programmed to play either the equilibrium solution or a fictitious play (FP) learning algorithm designed to take advantage of poor play. The results show that players did not adopt the cutoff-type strategies predicted by the equilibrium solution;rather they made considerable "errors'' by: Betting when they should have checked, checking when they should have bet, and calling when they should have folded. There is no evidence that aggregate performance improved over time in either condition although considerable individual differences were observed among subjects. Behavioral learning theory (BLT) cannot easily explain these individual differences and cognitive learning theory (CLT) is introduced to explain the apparent anomalies. Copyright (C) 2009 John Wiley & Sons, Ltd.
Characteristic features of feedforward artificial neural networks, acting as universal function approximators, are presented. The problem under consideration concerns inverse kinematics of a two-link planar manipulato...
详细信息
ISBN:
(纸本)9781424481545
Characteristic features of feedforward artificial neural networks, acting as universal function approximators, are presented. The problem under consideration concerns inverse kinematics of a two-link planar manipulator. As shown in the article, a two-layer, feedforward neural network is able to learn the nonlinear mapping between the end-effector position domain and the joint angle domain of the manipulator. However, the necessary condition for achieving the required approximation quality is the selection of suitable network structure, especially with regard to the number of nonlinear, sigmoidal units in its hidden layer. Effects of learning algorithm and choice of learning data set on the network performance are also demonstrated.
Doors are important landmarks for robot self localization and navigation in indoor environments. Existing algorithms for door detection are often limited to restricted environments. They do not consider the large intr...
详细信息
ISBN:
(纸本)9789896740214
Doors are important landmarks for robot self localization and navigation in indoor environments. Existing algorithms for door detection are often limited to restricted environments. They do not consider the large intra-class variability of doors. In this paper we present a camera- and laser-based approach which allows finding more than 82% of all doors with a false positive rate less than 3% in static test sets. By using different door perspectives from a moving robot, we detect more than 90% of doors with a very low false detection rate.
This paper belongs to neural technology and pattern recognition. It contains the description learning algorithm of back propagation. The most we pay our attention on programming algorithm.
ISBN:
(纸本)9781424445165
This paper belongs to neural technology and pattern recognition. It contains the description learning algorithm of back propagation. The most we pay our attention on programming algorithm.
On the basis of analyzing the principles of the quantum rotation gates and quantum controlled-NOT gates, an improved design for CNOT gated quantum neural networks model is proposed and a smart algorithm for it is deri...
详细信息
On the basis of analyzing the principles of the quantum rotation gates and quantum controlled-NOT gates, an improved design for CNOT gated quantum neural networks model is proposed and a smart algorithm for it is derived in our paper, based on the gradient descent algorithm. In the improved model, the input information is expressed by the qubits, which, as the control qubits after being rotated by the rotation gate, control the qubits in the hidden layer to reverse. The qubits in the hidden layer, as the control qubits after being rotated by the rotation gate, control the qubits in the output layer to reverse. The networks output is described by the probability amplitude of state |1 > in the output layer. It has been shown in two application examples of pattern recognition and function approximation that the proposed model is superior to the standard error back-propagation networks with regard to their convergence rate, number of iterations, approximation ability, and robustness.
A conventional way to enhance the steering features (hence optimize the vehicle dynamics) and steering feeling has been realized with EPS (Electric Power Steering) Systems. Another milestone of steering systems is the...
详细信息
A conventional way to enhance the steering features (hence optimize the vehicle dynamics) and steering feeling has been realized with EPS (Electric Power Steering) Systems. Another milestone of steering systems is the steer-by-wire steering system, which has no mechanical connection between the steering wheel and tires. Steer-by-wire systems offer many additional desirable steering characteristics. In this paper, a steer-by-wire implementation with new functions will be introduced. Furthermore first results with real-time experimental examples will be elucidated in detail.
作者：
Seo, Kwang-KyuAhn, Beum JunSangmyung Univ
Div Comp Informat & Telecommun Engn Dept Ind Informat & Syst engn San 98-20Anso Dong Cheonan 330720 Chungnam South Korea
Life cycle concerns have been realized a major issue of increasing importance. Life cycle cost as analytical method has been developed to enable comprehensive cost analysis to improve economic performance of products ...
详细信息
Life cycle concerns have been realized a major issue of increasing importance. Life cycle cost as analytical method has been developed to enable comprehensive cost analysis to improve economic performance of products during their life cycle. This paper present a learning algorithm based estimation method for maintenance cost as life cycle cost of product concepts. In order to develop the proposed method, we identify some attributes that represent corrective maintainability of product concepts and add them to the product attributes used to make a selection amongst product concepts. From the list of all the product attributes, 24 product attributes strongly correlated with maintenance cost are chosen. To estimate maintenance cost of product concepts, the selected product attributes are used as inputs and maintenance cost are used as outputs in a learning model based on based on artificial neural networks. The proposed approach does not replace the detailed cost estimation but it would give some cost-effective decision making for product concepts. (c) 2006 Elsevier Ltd. All rights reserved.
In this paper, we present a technique to analyze and correlate the different types of computer log files. Log files are generated from servers and network devices to record operations that occur in the computers and n...
详细信息
ISBN:
(纸本)9781424463671
In this paper, we present a technique to analyze and correlate the different types of computer log files. Log files are generated from servers and network devices to record operations that occur in the computers and networks. As log files are too enormous to manualize, we develop a tool to maximize accuracy as well as efficiency while high speed processing is the goal. Firstly, we must improve the accuracy by using learning algorithms to classify the normal operations from the abnormal ones such algorithms include tf-idf, association rules, k-means clustering, and decision tree. Secondly, we may adapt for less accuracy in order to gain speed for both with and/or without parallel processing techniques. We also construct an adaptive learning algorithm to update the model. Then we flush out out-of-date model while the logs are being captured and processed. The result can achieve the goal as they can reach about 30-40％ in real-time processing with nearly zero false positive results.
暂无评论