Ieee transactions on neural networks文章索引

Stochastic competitive learning [0.03%] 随机竞争学习

B Kosko B Kosko

Competitive learning systems are examined as stochastic dynamical systems. This includes continuous and discrete formulations of unsupervised, supervised, and differential competitive learning systems. These systems estimate an unknown prob...

IEEE transactions on neural networks. 1991;2(5):522-9. DOI:10.1109/72.134289 1991

Equilibrium characterization of dynamical neural networks and a systematic synthesis procedure for associative memories [0.03%] 动力学神经网络的平衡特征及联想记忆系统的合成方法

S I Sudharsanan,M K Sundareshan S I Sudharsanan

Several novel results concerning the characterization of the equilibrium conditions of a continuous-time dynamical neural network model and a systematic procedure for synthesizing associative memory networks with nonsymmetrical interconnect...

IEEE transactions on neural networks. 1991;2(5):509-21. DOI:10.1109/72.134288 1991

Invariance and neural nets [0.03%] 不变性和神经网络

E Barnard,D Casasent E Barnard

Application of neural nets to invariant pattern recognition is considered. The authors study various techniques for obtaining this invariance with neural net classifiers and identify the invariant-feature technique as the most suitable for ...

IEEE transactions on neural networks. 1991;2(5):498-508. DOI:10.1109/72.134287 1991

An information criterion for optimal neural network selection [0.03%] 最优神经网络选择的信息准则

D B Fogel D B Fogel

The choice of an optimal neural network design for a given problem is addressed. A relationship between optimal network design and statistical model identification is described. A derivative of Akaike's information criterion (AIC) is given....

IEEE transactions on neural networks. 1991;2(5):490-7. DOI:10.1109/72.134286 1991

Convergence of learning algorithms with constant learning rates [0.03%] 恒定学习率下学习算法的收敛性

C M Kuan,K Hornik C M Kuan

The behavior of neural network learning algorithms with a small, constant learning rate, epsilon, in stationary, random input environments is investigated. It is rigorously established that the sequence of weight estimates can be approximat...

IEEE transactions on neural networks. 1991;2(5):484-9. DOI:10.1109/72.134285 1991

A multilayer neural network with piecewise-linear structure and back-propagation learning [0.03%] 一种分段线性结构的多层神经网络及其反向传播算法

R Batruni R Batruni

A multilayer neural network which is given a two-layer piecewise-linear structure for every cascaded section is proposed. The neural networks have nonlinear elements that are neither sigmoidal nor of a signum type. Each nonlinear element is...

IEEE transactions on neural networks. 1991;2(3):395-403. DOI:10.1109/72.97915 1991

A general weight matrix formulation using optimal control [0.03%] 基于最优控制的通用权重矩阵分析方法

O Farotimi,A Dembo,T Kailath O Farotimi

Classical methods from optimal control theory are used in deriving general forms for neural network weights. The network learning or application task is encoded in a performance index of a general structure. Consequently, different instance...

IEEE transactions on neural networks. 1991;2(3):378-94. DOI:10.1109/72.97914 1991

A neural network approach to statistical pattern classification by ;semiparametric' estimation of probability density functions [0.03%] 一种基于半参数概率密度函数估计的统计模式分类神经网络方法研究

H C Traven H C Traven

A method for designing near-optimal nonlinear classifiers, based on a self-organizing technique for estimating probability density functions when only weak assumptions are made about the densities, is described. The method avoids disadvanta...

IEEE transactions on neural networks. 1991;2(3):366-77. DOI:10.1109/72.97913 1991

Handwritten alphanumeric character recognition by the neocognitron [0.03%] 新的神经网络在手写字符识别中的应用研究

K Fukushima,N Wake K Fukushima

A pattern recognition system which works with the mechanism of the neocognitron, a neural network model for deformation-invariant visual pattern recognition, is discussed. The neocognition was developed by Fukushima (1980). The system has b...

IEEE transactions on neural networks. 1991;2(3):355-65. DOI:10.1109/72.97912 1991

Fast training algorithms for multilayer neural nets [0.03%] 多层神经网络的快速训练算法

R P Brent R P Brent

An algorithm that is faster than back-propagation and for which it is not necessary to specify the number of hidden units in advance is described. The relationship with other fast pattern-recognition algorithms, such as algorithms based on ...

IEEE transactions on neural networks. 1991;2(3):346-54. DOI:10.1109/72.97911 1991