We derive a general learning algorithm for training a fuzzified feedforward neural network that has fuzzy inputs, fuzzy targets, and fuzzy connection weights. The derived algorithm is applicable to the learning of fuz...
详细信息
We derive a general learning algorithm for training a fuzzified feedforward neural network that has fuzzy inputs, fuzzy targets, and fuzzy connection weights. The derived algorithm is applicable to the learning of fuzzy connection weights with various shapes such as triangular and trapezoid. First we briefly describe how a feedforward neural network can be fuzzified. inputs, targets, and connection weights in the fuzzified neural network can be fuzzy numbers. Next we define a cost function that measures the difference between a fuzzy target vector and an actual fuzzy output vector Then we derive a learning algorithm from the cost function for adjusting fuzzy connection weights. Finally we show some results of computer simulations.
In this paper, the complexity of learning in the feedforward PLN network is investigated by using Markov chain theory, when its training samples are incomplete (i.e., a network with hidden nodes). We present a learnin...
详细信息
In this paper, the complexity of learning in the feedforward PLN network is investigated by using Markov chain theory, when its training samples are incomplete (i.e., a network with hidden nodes). We present a learning algorithm. A formula for computing the average number of steps that the learning algorithm converges is obtained when the PLN network exists a solution. In the probabilistic sense, the completeness of the learning algorithm is proved. Some computer simulations are given to verify the analysis.
This paper deals with the drive control of an autonomous mobile robot. An autonomous mobile robot is one of the intelligent robots that need abilities to recognize and to adapt to surrounding environment. We propose a...
详细信息
This paper deals with the drive control of an autonomous mobile robot. An autonomous mobile robot is one of the intelligent robots that need abilities to recognize and to adapt to surrounding environment. We propose a new approach to meeting these needs. This approach is based on a forecast learning fuzzy control. The environment can be classified into several characteristic patterns and our robot has sets of control rules for each pattern beforehand. The robot integrates these sets into a single set using degrees of matching between the current environment and each pattern. The robot forecasts whether it will drive safely or not by prediction, by using the integrated control rules. The robot considers the results of the forecast, and then adjusts the conclusion parts of the integrated control rules in order to drive more safely in such an environment. In this paper, to find the efficacy of our new approach, the simulation results of the drive control of the robot and the experimental results on indoor routes are shown.
An algorithm for the training of multilayered neural networks solely based on linear algebraic methods is presented. Its convergence speed up to a certain limit of learning accuracy is orders of magnitude better than ...
详细信息
An algorithm for the training of multilayered neural networks solely based on linear algebraic methods is presented. Its convergence speed up to a certain limit of learning accuracy is orders of magnitude better than that of the classical back propagation. Furthermore, its learning aptitude increases with the number of internal nodes in the network (contrary to backprop). Especially if the network includes a hidden layer with more nodes than the number of examples to be learned and if the number of nodes in succeeding layers decreases monotonically, the presented algorithm in general finds an exact solution.
Training neural networks is a NP complete problem. A learning algorithm is proposed in this paper. Theoretic analysis and simulation results show that this kind of algorithm, which is used to train large BP neural net...
详细信息
ISBN:
(纸本)780003285X
Training neural networks is a NP complete problem. A learning algorithm is proposed in this paper. Theoretic analysis and simulation results show that this kind of algorithm, which is used to train large BP neural network, can speed up the learning rate and gain accurate results.
We derive a new self-organizing learning algorithm that maximizes the information transferred in a network of nonlinear units. The algorithm does not assume any knowledge of the input distributions, and is defined her...
详细信息
We derive a new self-organizing learning algorithm that maximizes the information transferred in a network of nonlinear units. The algorithm does not assume any knowledge of the input distributions, and is defined here for the zero-noise limit. Under these conditions, information maximization has extra properties not found in the linear case (Linsker 1989). The nonlinearities in the transfer function are able to pick up higher-order moments of the input distributions and perform something akin to true redundancy reduction between units in the output representation. This enables the network to separate statistically independent components in the inputs: a higher-order generalization of principal components analysis. We apply the network to the source separation (or cocktail party) problem, successfully separating unknown mixtures of up to 10 speakers. We also show that a variant on the network architecture is able to perform blind deconvolution (cancellation of unknown echoes and reverberation in a speech signal). Finally, we derive dependencies of information transfer on time delays. We suggest that information maximization provides a unifying framework for problems in ''blind'' signal processing.
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.
Evaluation is a critical issue in any information systems. This problem has become more and more important with the rapid development of multimedia systems. Feature measures and similarity measures play a central role...
详细信息
ISBN:
(纸本)0819419702
Evaluation is a critical issue in any information systems. This problem has become more and more important with the rapid development of multimedia systems. Feature measures and similarity measures play a central role in content-based retrieval. Evaluation of their effectiveness and efficiency then become a key issue in assessing the performance of a content- based multimedia system. A learning algorithm has been studied to find a suitable and hopefully the best similarity function for a given set of feature measure and a given set of training data set.
Training neural network is a NP complete problem[1][3].A learning algorithm is proposed in this *** analysis and simulation results show that this kind of algorithm, which is used to train large BP neural network,can ...
详细信息
ISBN:
(纸本)0780312333
Training neural network is a NP complete problem[1][3].A learning algorithm is proposed in this *** analysis and simulation results show that this kind of algorithm, which is used to train large BP neural network,can speed up the learning rate and gain accurate results.
This paper describes a learning algorithm to be applied in process control techniques, covering several topics of control applications such as system identification, or process supervision in a simple and useful way w...
详细信息
暂无评论