Ieee transactions on neural networks文章索引

Selecting useful groups of features in a connectionist framework [0.03%] 连接主义框架下有用特征组合的选择

Debrup Chakraborty,Nikhil R Pal Debrup Chakraborty

Suppose for a given classification or function approximation (FA) problem data are collected using l sensors. From the output of the ith sensor, ni features are extracted, thereby generating p = sigma li = 1 ni features, so for the task we ...

IEEE transactions on neural networks. 2008 Mar;19(3):381-96. DOI:10.1109/TNN.2007.910730 2008

Classification of radar clutter using neural networks [0.03%] 基于神经网络的雷达杂波分类

S Haykin,C Deng S Haykin

A classifier that incorporates both preprocessing and postprocessing procedures as well as a multilayer feedforward network (based on the back-propagation algorithm) in its design to distinguish between several major classes of radar return...

IEEE transactions on neural networks. 1991;2(6):589-600. DOI:10.1109/72.97936 1991

Optimal training of thresholded linear correlation classifiers [0.03%] 阈值线性相关分类器的优化训练方法研究

T H Hildebrandt T H Hildebrandt

A closed-form solution for improved pattern recognition that reduces the training time to a single epoch (one presentation of each of the training patterns) is presented. It is shown that the corresponding hardware requirements are no great...

IEEE transactions on neural networks. 1991;2(6):577-88. DOI:10.1109/72.97935 1991

A general regression neural network [0.03%] 一般的回归神经网络

D F Specht D F Specht

A memory-based network that provides estimates of continuous variables and converges to the underlying (linear or nonlinear) regression surface is described. The general regression neural network (GRNN) is a one-pass learning algorithm with...

IEEE transactions on neural networks. 1991;2(6):568-76. DOI:10.1109/72.97934 1991

Guaranteed recall of all training pairs for bidirectional associative memory [0.03%] 双向联想记忆的全训练对保证回忆性

Y F Wang,J R Cruz,J R Mulligan Y F Wang

Necessary and sufficient conditions are derived for the weights of a generalized correlation matrix of a bidirectional associative memory (BAM) which guarantee the recall of all training pairs. A linear programming/multiple training (LP/MT)...

IEEE transactions on neural networks. 1991;2(6):559-67. DOI:10.1109/72.97933 1991

Bounds on the number of samples needed for neural learning [0.03%] 神经学习中所需样本数量的界值分析

K G Mehrotra,C K Mohan,S Ranka K G Mehrotra

The relationship between the number of hidden nodes in a neural network, the complexity of a multiclass discrimination problem, and the number of samples needed for effect learning are discussed. Bounds for the number of samples needed for ...

IEEE transactions on neural networks. 1991;2(6):548-58. DOI:10.1109/72.97932 1991

A neural network approach to a Bayesian statistical decision problem [0.03%] 贝叶斯统计决策问题的神经网络方法研究

S Miyake,F Kanaya S Miyake

Generalized mean-squared error (GMSE) objective functions are proposed that can be used in neural networks to yield a Bayes optimal solution to a statistical decision problem characterized by a generic loss function.

IEEE transactions on neural networks. 1991;2(5):538-40. DOI:10.1109/72.134293 1991

A new back-propagation algorithm with coupled neuron [0.03%] 一种新的耦合神经元反向传播算法

M Fukumi,S Omatu M Fukumi

A novel neuron model and its learning algorithm are presented. They provide a novel approach for speeding up convergence in the learning of layered neural networks and for training networks of neurons with a nondifferentiable output functio...

IEEE transactions on neural networks. 1991;2(5):535-8. DOI:10.1109/72.134292 1991

Worst-case convergence times for Hopfield memories [0.03%] 霍普费尔德存贮系统的最坏情况收敛时间

P Floreen P Floreen

The worst-case upper bound on the convergence time of Hopfield associative memories is improved to half of its previously known value. Also, the consequences of allowing ;don't know' bits in both the input and the output are considered.

IEEE transactions on neural networks. 1991;2(5):533-5. DOI:10.1109/72.134291 1991

CMAC-based adaptive critic self-learning control [0.03%] 基于CMAC的自适应论理自学习控制

C S Lin,H Kim C S Lin

A technique that integrates the cerebellar model articulation controller (CMAC) into a self-learning control scheme developed by A.G. Barto et al. (IEEE Trans. Syst. Man., Cybern., vol.SMC-13, p.834-46, Sept./Oct. 1983) is presented. Instea...

IEEE transactions on neural networks. 1991;2(5):530-3. DOI:10.1109/72.134290 1991