Ieee transactions on neural networks文章索引

Improving the error backpropagation algorithm with a modified error function [0.03%] 采用改进误差函数优化反向传播算法

S H Oh S H Oh

This letter proposes a modified error function to improve the error backpropagation (EBP) algorithm of multilayer perceptrons (MLPs) which suffers from slow learning speed. To accelerate the learning speed of the EBP algorithm, the proposed...

IEEE transactions on neural networks. 1997;8(3):799-803. DOI:10.1109/72.572117 1997

Hierarchical graph visualization using neural networks [0.03%] 基于神经网络的层次图可视化方法

K Kusnadi,J D Carothers,F Chow K Kusnadi

An algorithm based on a Hopfield network for solving the hierarchical graph visualization problem is presented. It simultaneously minimizes the number of crossings and total path length to produce two-dimensional drawings easily interpreted...

IEEE transactions on neural networks. 1997;8(3):794-9. DOI:10.1109/72.572116 1997

A new approach to Kanerva's sparse distributed memory [0.03%] 一种新的Kanerva稀疏分布式内存方法

T A Hely,D J Willshaw,G M Hayes T A Hely

The sparse distributed memory (SDM) was originally developed to tackle the problem of storing large binary data patterns. The model succeeded well in storing random input data. However, its efficiency, particularly in handling nonrandom dat...

IEEE transactions on neural networks. 1997;8(3):791-4. DOI:10.1109/72.572115 1997

Primal and dual assignment networks [0.03%] 原始分配网络与对偶分配网络

J Wang J Wang

This paper presents two recurrent neural networks for solving the assignment problem. Simplifying the architecture of a recurrent neural network based on the primal assignment problem, the first recurrent neural network, called the primal a...

IEEE transactions on neural networks. 1997;8(3):784-90. DOI:10.1109/72.572114 1997

An improved recurrent neural network for M-PAM symbol detection [0.03%] 一种改进的递归神经网络M-PAM符号检测方法

K Hacioglu K Hacioglu

In this paper, a fully connected recurrent neural network (RNN) is presented for the recovery of M-ary pulse amplitude modulated (M-PAM) signals in the presence of intersymbol interference and additive white Gaussian noise. The network make...

IEEE transactions on neural networks. 1997;8(3):779-83. DOI:10.1109/72.572113 1997

Orthogonal projections applied to the assignment problem [0.03%] 正交投影在线性分配中的应用

W J Wolfe,R M Ulmer W J Wolfe

This paper presents a significant improvement to the traditional neural approach to the assignment problem (AP). The technique is based on identifying the feasible space (F) with a linear subspace of R(n(2)), and then analyzing the orthogon...

IEEE transactions on neural networks. 1997;8(3):774-8. DOI:10.1109/72.572112 1997

SOIM: a self-organizing invertible map with applications in active vision [0.03%] 具有主动视觉应用的自组织互逆映射(SOIM)

N Srinivasa,R Sharma N Srinivasa

We propose a novel neural network, called the self-organized invertible map (SOIM), that is capable of learning many-to-one functionals mappings in a self-organized and online fashion. The design and performance of the SOIM are highlighted ...

IEEE transactions on neural networks. 1997;8(3):758-73. DOI:10.1109/72.572111 1997

Real-time classification of rotating shaft loading conditions using artificial neural networks [0.03%] 基于人工神经网络的旋转轴实时载荷状态分类方法研究

A C McCormick,A K Nandi A C McCormick

Vibration analysis can give an indication of the condition of a rotating shaft highlighting potential faults such as unbalance and rubbing. Faults may however only occur intermittently and consequently to detect these requires continuous mo...

IEEE transactions on neural networks. 1997;8(3):748-57. DOI:10.1109/72.572110 1997

Temporal and spatial stability in translation invariant linear resistive networks [0.03%] 具有时不变性的线性电阻网络的时空稳定性分析

M K Solak M K Solak

Simple algebraic methods are proposed to evaluate the temporal and spatial stability of translation invariant linear resistive networks. Temporal stability is discussed for a finite number of nodes n. The proposed method evaluates stability...

IEEE transactions on neural networks. 1997;8(3):736-47. DOI:10.1109/72.572109 1997

Supervised neural networks for the classification of structures [0.03%] 监督神经网络在分类中的应用研究

A Sperduti,A Starita A Sperduti

Standard neural networks and statistical methods are usually believed to be inadequate when dealing with complex structures because of their feature-based approach. In fact, feature-based approaches usually fail to give satisfactory solutio...

IEEE transactions on neural networks. 1997;8(3):714-35. DOI:10.1109/72.572108 1997