历史查询   



 为了更好的帮助您理解掌握查询词或其译词在地道英语中的实际用法，我们为您准备了出自英文原文的大量英语例句，供您参考。 
This paper presents a Bayesian neural network framework which accounts for input noise provided that a model of the noise process exists.


The Bayesian neural network is designed to learn very quickly and incrementally.


The "naive" Bayesian classifier typically outperforms the basic Bayesian neural network since iterations in network make too many mistakes.


The Bayesian neural network uses more sophisticated combination function than Hopfield's neural network and uses more economically the available information.


The performance of the Bayesian neural network in four medical domains is compared with various classification methods.

 更多 


 With neural networks, the main difficult in improving the model generalization capability is controlling the complexity of the model. This paper investigates a Bayesian neural network learning for nonparametric regression. Prior knowledge about the model parameters can be incorporated within Bayesian inference and combined with training data to control complexity of different parts of the model. A Markov chain Monte Carlo algorithm is used to optimize model control parameters and obtain... With neural networks, the main difficult in improving the model generalization capability is controlling the complexity of the model. This paper investigates a Bayesian neural network learning for nonparametric regression. Prior knowledge about the model parameters can be incorporated within Bayesian inference and combined with training data to control complexity of different parts of the model. A Markov chain Monte Carlo algorithm is used to optimize model control parameters and obtain the predictive distribution. We show that the complexity of the models adapts to the complexity of the data and produces good results on five noisy test functions in two dimension. The performance and advantage of this approach are compared with conventional neural network methods.  提高神经网络模型推广能力的关键是控制模型的复杂度。该文探索了贝叶斯神经网络的非参数回归的建模方法,通过融入模型参数的先验知识,在给定数据样本及模型假设下进行后验概率的贝叶斯推理,使用马尔可夫链蒙特卡罗算法来优化模型控制参数,实现了对神经网络模型中不同部分复杂度的控制,获得了模型参数的后验分布及预测分布。在5个含噪二维函数回归问题上的应用显示了模型的复杂度能根据数据的复杂度而自适应调整,并给出了较好的预测结果。  Some key aspects in the Bayesian Maximum Likelihood Expectation Maximization Method (ML EM)for positron emission tomography(PET)imaging were investigated.In order to overcome the limitation of traditional solutions to estimate Maximum a Posteriori(MAP),a Bayesian neural network(BNN) algorithm was proposed for PET imaging.In addition to real valued source intensities,binary variables were introduced to protect the information of the edges.These two different kinds of variables can be obtained by... Some key aspects in the Bayesian Maximum Likelihood Expectation Maximization Method (ML EM)for positron emission tomography(PET)imaging were investigated.In order to overcome the limitation of traditional solutions to estimate Maximum a Posteriori(MAP),a Bayesian neural network(BNN) algorithm was proposed for PET imaging.In addition to real valued source intensities,binary variables were introduced to protect the information of the edges.These two different kinds of variables can be obtained by a coupled gradient network composed of two interacting recurrent networks corresponding to the two kinds of variables respectively.Compared with ML EM reconstruction,the BNN results showed higher quality.  从MLEM重建算法入手,分析了贝叶斯模型的一些关键点.针对采用传统方法求解MAP问题的局限性,提出一种用于正电子成像的贝叶斯神经网络(BNN)重建算法.为了保留边缘信息,引入了二进制的保边缘变量,并应用共轭神经网络求解.模拟的重建结果表明,应用这种算法可以得到比MLEM算法更好的重建图像.  Spam filtering is an important task in the application of Internet, which receives increasing emphasis. In this paper a method of spam filtering based on the Bayesian Neural Network (BNN) algorithm is presented. The Bayesian approach is used for neural network to learn from the user given training spam/normal email set. And the number of features needed as the input of the BNN model is reduced effectively through the proposed feature selection approach, where information gain is chosen... Spam filtering is an important task in the application of Internet, which receives increasing emphasis. In this paper a method of spam filtering based on the Bayesian Neural Network (BNN) algorithm is presented. The Bayesian approach is used for neural network to learn from the user given training spam/normal email set. And the number of features needed as the input of the BNN model is reduced effectively through the proposed feature selection approach, where information gain is chosen as a criterion. The result of the experiment shows that the method in this paper can filter spam effectively.  垃圾邮件过滤是当前互联网应用中急需解决的一个重要课题,日益受到人们的关注。本文提出了一种基于贝叶斯神经网络BNN(BayesianNeuralNetwork)的垃圾邮件过滤方法,利用贝叶斯推理和神经网络相结合的贝叶斯神经网络算法对用户给定的正常/垃圾邮件集合进行训练,得到邮件过滤模型。并且提出了一种有效的特征选择方法,采用信息增益准则,有效降低了特征维数。经过实验测试,本文提出的方法可以实现对垃圾邮件的有效过滤。   << 更多相关文摘 
相关查询  



