Ieee transactions on neural networks文章索引

A new evolutionary system for evolving artificial neural networks [0.03%] 一种新的用于人工神经网络进化的系统

X Yao,Y Liu X Yao

This paper presents a new evolutionary system, i.e., EPNet, for evolving artificial neural networks (ANNs). The evolutionary algorithm used in EPNet is based on Fogel's evolutionary programming (EP). Unlike most previous studies on evolving...

IEEE transactions on neural networks. 1997;8(3):694-713. DOI:10.1109/72.572107 1997

Quantum neural networks (QNNs): inherently fuzzy feedforward neural networks [0.03%] 量子神经网络(QNNs)：本质上具有模糊性的前馈神经网络

G Purushothaman,N B Karayiannis G Purushothaman

This paper introduces quantum neural networks (QNNs), a class of feedforward neural networks (FFNNs) inherently capable of estimating the structure of a feature space in the form of fuzzy sets. The hidden units of these networks develop qua...

IEEE transactions on neural networks. 1997;8(3):679-93. DOI:10.1109/72.572106 1997

On self-organizing algorithms and networks for class-separability features [0.03%] 自组织类间分离特征提取算法和网络研究

C Chatterjee,V P Roychowdhury C Chatterjee

We describe self-organizing learning algorithms and associated neural networks to extract features that are effective for preserving class separability. As a first step, an adaptive algorithm for the computation of Q(-1/2) (where Q is the c...

IEEE transactions on neural networks. 1997;8(3):663-78. DOI:10.1109/72.572105 1997

Neural-network feature selector [0.03%] 神经网络特征选择器

R Setiono,H Liu R Setiono

Feature selection is an integral part of most learning algorithms. Due to the existence of irrelevant and redundant attributes, by selecting only the relevant attributes of the data, higher predictive accuracy can be expected from a machine...

IEEE transactions on neural networks. 1997;8(3):654-62. DOI:10.1109/72.572104 1997

Fast parallel off-line training of multilayer perceptrons [0.03%] 多层知觉的快速并行脱机训练

S McLoone,G W Irwin S McLoone

Various approaches to the parallel implementation of second-order gradient-based multilayer perceptron training algorithms are described. Two main classes of algorithm are defined involving Hessian and conjugate gradient-based methods. The ...

IEEE transactions on neural networks. 1997;8(3):646-53. DOI:10.1109/72.572103 1997

Constructive algorithms for structure learning in feedforward neural networks for regression problems [0.03%] 用于回归问题的前馈神经网络结构学习的构造算法

T Y Kwok,D Y Yeung T Y Kwok

In this survey paper, we review the constructive algorithms for structure learning in feedforward neural networks for regression problems. The basic idea is to start with a small network, then add hidden units and weights incrementally unti...

IEEE transactions on neural networks. 1997;8(3):630-45. DOI:10.1109/72.572102 1997

On convergence properties of pocket algorithm [0.03%] 论pocket算法的收敛性

M Muselli M Muselli

The problem of finding optimal weights for a single threshold neuron starting from a general training set is considered. Among the variety of possible learning techniques, the pocket algorithm has a proper convergence theorem which asserts ...

IEEE transactions on neural networks. 1997;8(3):623-9. DOI:10.1109/72.572101 1997

Supervised learning of perceptron and output feedback dynamic networks: a feedback analysis via the small gain theorem [0.03%] 基于小增益理论的受控单神经元模型与输出反馈动态系统的稳定性分析

M Rupp,A H Sayed M Rupp

This paper provides a time-domain feedback analysis of the perceptron learning algorithm and of training schemes for dynamic networks with output feedback. It studies the robustness performance of the algorithms in the presence of uncertain...

IEEE transactions on neural networks. 1997;8(3):612-22. DOI:10.1109/72.572100 1997

Neural networks for convex hull computation [0.03%] 用于凸包计算的神经网络

Y Leung,J S Zhang,Z B Xu Y Leung

Computing convex hull is one of the central problems in various applications of computational geometry. In this paper, a convex hull computing neural network (CHCNN) is developed to solve the related problems in the N-dimensional spaces. Th...

IEEE transactions on neural networks. 1997;8(3):601-11. DOI:10.1109/72.572099 1997

On solving systems of linear inequalities with artificial neural networks [0.03%] 用人工神经网络求解线性不等式组问题

G Labonte G Labonte

The implementation of the relaxation-projection algorithm by artificial neural networks to solve sets of linear inequalities is examined. The different versions of this algorithm are described, and theoretical convergence results are given....

IEEE transactions on neural networks. 1997;8(3):590-600. DOI:10.1109/72.572098 1997