In recent years, technology developments are more rapidly. How to learn and obtain desired knowledge efficiently has become an important but complicated problem. We hope that there are methods can give us some suggest...
详细信息
In recent years, technology developments are more rapidly. How to learn and obtain desired knowledge efficiently has become an important but complicated problem. We hope that there are methods can give us some suggestions about how to learn knowledge efficiently. In this paper, we introduced some learning behavior of people, and then use our designed Effective learning Curve Model to imitate this learning phenomenon. Using our learning function model, we can imitate people's learning behavior through pretesting. Every one has different learning behavior functions on learning distinct courses. Different learning sequence of courses will cause different learning efficiency. From this view, we proposed Max learning Efficiency Slope First algorithm (MLESFA) by differential learning functions to give people some suggestions about courses learning sequence and obtain desired knowledge efficiently. These algorithms also can help us to understand how much time we have to spend on each course in order to get better learning efficiency under time limitation. Finally, we make some learning example and compare simulation results with other courses learning algorithms. From the simulation results, we can see that our MLESFA algorithm has better learning efficiency than others.
The regular fuzzy neural network (RFNN) is a kind of fuzzy neural network by fuzzifying the feed-forward neural network. The RFNN can directly deal with the language information and it has the merits of fuzzy system a...
详细信息
The regular fuzzy neural network (RFNN) is a kind of fuzzy neural network by fuzzifying the feed-forward neural network. The RFNN can directly deal with the language information and it has the merits of fuzzy system and neural network. It is presented a fast learning algorithm based on the extreme learning machine (ELM) for the RFNN in this paper. The RFNN referred here is a three-layer feed-forward fuzzy neural network and the connected weights in the RFNN are all fuzzy numbers. A simulation example is given to approximately realize the fuzzy if-then rules by the RFNN. The results show that the RFNN trained by the proposed algorithm has good performance and approximation ability.
In this study, the linguistic information feed-back-based dynamical fuzzy system (LIFBDFS) proposed earlier by the authors is first introduced. The principles of alpha-level sets and backpropagation through time appro...
详细信息
In this study, the linguistic information feed-back-based dynamical fuzzy system (LIFBDFS) proposed earlier by the authors is first introduced. The principles of alpha-level sets and backpropagation through time approach are also briefly discussed. We next employ these two methods to derive an explicit learning algorithm for the feedback parameters of the LIFBDFS. With this training algorithm, our LIFBDFS indeed becomes a potential candidate in solving real-time modeling and prediction problems.
The paper deals with the problem of fault tolerance in a multilayer perceptron network. Although it already possesses a reasonable fault tolerance capability, it may be insufficient in particularly critical applicatio...
详细信息
The paper deals with the problem of fault tolerance in a multilayer perceptron network. Although it already possesses a reasonable fault tolerance capability, it may be insufficient in particularly critical applications. Studies carried out by the authors have shown that the traditional backpropagation learning algorithm may entail the presence of a certain number of weights with a much higher absolute value thin the others. Further studies have shown that faults in these weights is the main cause of deterioration in the performance of the neural network. In other words, the main cause of incorrect network functioning on the occurrence of a fault is the non-uniform distribution of absolute values of weights in each layer. The paper proposes a learning algorithm which updates the weights, distributing their absolute values as uniformly as possible in each layer. Tests performed on benchmark test sets have shown the considerable increase in fault tolerance obtainable with the proposed approach as compared with the traditional backpropagation algorithm and with some of the most efficient fault tolerance approaches to be found in literature. (C) 1999 Elsevier Science Ltd. All rights: reserved.
In this paper, a middle-mapping learning algorithm for cellular associative memories is *** algorithm makes full use of the properties of the cellular neural network so that the associative memory has some advantages ...
详细信息
In this paper, a middle-mapping learning algorithm for cellular associative memories is *** algorithm makes full use of the properties of the cellular neural network so that the associative memory has some advantages compared with the memory designed by the outer product method. It can guarantee each prototype is stored-at an equilibrium point. In the practical implementation, it is easy to build up the circuit because the weight matrix presenting the connection between cells is not symmetric. The synchronous updating rule makes its associative speed very fast compared to the Hopfield associative memory.
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.
The mean field theory (MFT) learning algorithm is elaborated and explored with respect to a variety of tasks. MFT is benchmarked against the back-propagation learning algorithm (BP) on two different feature recognitio...
详细信息
The mean field theory (MFT) learning algorithm is elaborated and explored with respect to a variety of tasks. MFT is benchmarked against the back-propagation learning algorithm (BP) on two different feature recognition problems: two-dimensional mirror symmetry and multidimensional statistical pattern classification. We find that while the two algorithms are very similar with respect to generalization properties, MFT normally requires a substantially smaller number of training epochs than BP. Since the MFT model is bidirectional, rather than feed-forward, its use can be extended naturally from purely functional mappings to a content addressable memory. A network with N visible and N hidden units can store up to approximately 4 N patterns with good content-addressability. We stress an implementational advantage for MFT: it is natural for VLSI circuitry.
Fault diagnosis is becoming an important issue in industrial environment, and the accurate diagnosis is the most significant part in fault handling. This article discusses a fault detection and diagnosis problem for m...
详细信息
Fault diagnosis is becoming an important issue in industrial environment, and the accurate diagnosis is the most significant part in fault handling. This article discusses a fault detection and diagnosis problem for manufacturing systems taking into account rapid detection and speed performances of fault isolation with minimum ambiguity. However, in many complex real plants, it may not be possible to discover accurately the causes of probable faults. The accuracy of fault or fault detection by the traditional approaches is not adequate. Considering the quality effect of the learning algorithm, a new hybrid neural network approach is developed using the integration of a regression task for classification accuracy. Two models of neural networks: gradient descent and momentum & adaptive learning rate and Levenberg-Marquardt are investigated and compared. The performance of the proposed approach is evaluated using mean square error, convergence speed, and classification accuracy. The case study and experimental results are presented and discussed. A comparison with the Levenberg-Marquardt regression approach shows the importance of considering the proposed learning algorithm quality in the fault detection and diagnosis problem compared with those reported in the literature.
A novel learning algorithm for a neuron-weighted associative memory (NWAM) is presented. The learning procedure is casted as a global minimization, solved by a gradient descent rule. We also describe an analog neural ...
详细信息
A novel learning algorithm for a neuron-weighted associative memory (NWAM) is presented. The learning procedure is casted as a global minimization, solved by a gradient descent rule. We also describe an analog neural network to implement the learning method. Finally, some computer experiments are conducted.
An integrated fuzzy min-max neural network(IFMMNN) is developed to avoid the classification result influenced by the input sequence of training samples, and the learning algorithm can be used as pure clustering,pure c...
详细信息
An integrated fuzzy min-max neural network(IFMMNN) is developed to avoid the classification result influenced by the input sequence of training samples, and the learning algorithm can be used as pure clustering,pure classification, or a hybrid clustering classification. Three experiments are designed to realize the aim. The serial input of samples is changed to parallel input, and the fuzzy membership function is substituted by similarity matrix. The experimental results show its superiority in contrast with the original method proposed by Simpson.
暂无评论