Ieee transactions on neural networks文章索引

Morphological shared-weight networks with applications to automatic target recognition [0.03%] 应用于自动目标识别的形态共享权值神经网络研究

Y Won,P D Gader,P C Coffield Y Won

A shared-weight neural network based on mathematical morphology is introduced. The feature extraction process is learned by interaction with the classification process. Feature extraction is performed using gray-scale hit-miss transforms th...

IEEE transactions on neural networks. 1997;8(5):1195-203. DOI:10.1109/72.623220 1997

An ART1 microchip and its use in multi-ART1 systems [0.03%] 一种ART1微芯片及其在多ART1系统中的应用研究

T Serrano-Gotarrdeona,B Linares-Barranco T Serrano-Gotarrdeona

Recently, a real-time clustering microchip neural engine based on the ART1 architecture has been reported. However, that chip rendered an extremely high silicon area consumption of 1 cm(2), and consequently an extremely low yield of 6%. Red...

IEEE transactions on neural networks. 1997;8(5):1184-94. DOI:10.1109/72.623219 1997

Kernel orthonormalization in radial basis function neural networks [0.03%] 径向基函数神经网络中的核正交化

W Kaminski,P Strumillo W Kaminski

This paper deals with optimization of the computations involved in training radial basis function (RBF) neural networks. The main contribution of the reported work is the method for network weights calculation, in which the key idea is to t...

IEEE transactions on neural networks. 1997;8(5):1177-83. DOI:10.1109/72.623218 1997

Degree of population diversity - a perspective on premature convergence in genetic algorithms and its Markov chain analysis [0.03%] 种群多样性程度-过早收敛的遗传算法的新视角及其马尔可夫链分析

Y Leung,Y Gao,Z B Xu Y Leung

In this paper, a concept of degree of population diversity is introduced to quantitatively characterize and theoretically analyze the problem of premature convergence in genetic algorithms (GAs) within the framework of Markov chain. Under t...

IEEE transactions on neural networks. 1997;8(5):1165-76. DOI:10.1109/72.623217 1997

Are artificial neural networks black boxes? [0.03%] 人工神经网络是黑箱模型吗？

J M Benitez,J L Castro,I Requena J M Benitez

Artificial neural networks are efficient computing models which have shown their strengths in solving hard problems in artificial intelligence. They have also been shown to be universal approximators. Notwithstanding, one of the major criti...

IEEE transactions on neural networks. 1997;8(5):1156-64. DOI:10.1109/72.623216 1997

A minor subspace analysis algorithm [0.03%] 微子空间分析算法

F L Luo,R Unbehauen F L Luo

This paper proposes a learning algorithm which extracts adaptively the minor subspace spanned by the eigenvectors corresponding to the smallest eigenvalues of the autocorrelation matrix of an input signal. We show both analytically and by s...

IEEE transactions on neural networks. 1997;8(5):1149-55. DOI:10.1109/72.623215 1997

Objective functions for training new hidden units in constructive neural networks [0.03%] 用于训练构造型神经网络中新隐藏单元的目标函数

T Y Kwok,D Y Yeung T Y Kwok

In this paper, we study a number of objective functions for training new hidden units in constructive algorithms for multilayer feedforward networks. The aim is to derive a class of objective functions the computation of which and the corre...

IEEE transactions on neural networks. 1997;8(5):1131-48. DOI:10.1109/72.623214 1997

Learning rules for neuro-controller via simultaneous perturbation [0.03%] 基于同时扰动的学习规则在神经控制器中的应用研究

Y Maeda,R P De Figueiredo Y Maeda

This paper describes learning rules using simultaneous perturbation for a neurocontroller that controls an unknown plant. When we apply a direct control scheme by a neural network, the neural network must learn an inverse system of the unkn...

IEEE transactions on neural networks. 1997;8(5):1119-30. DOI:10.1109/72.623213 1997

A theoretical study of linear and nonlinear equalization in nonlinear magnetic storage channels [0.03%] 非线性磁记录通道的线性和非线性等化研究

S K Nair,J Moon S K Nair

We present methods to systematically design a feedforward neural-network detector from the knowledge of the channel characteristics. Its performance is compared with the conventional linear equalizer in a magnetic recording channel sufferin...

IEEE transactions on neural networks. 1997;8(5):1106-18. DOI:10.1109/72.623212 1997

An evaluation of the neocognitron [0.03%] 新型视网膜人工神经网络模型评测

D R Lovell,T Downs,A C Tsoi D R Lovell

We describe a sequence of experiments investigating the strengths and limitations of Fukushima's neocognitron as a handwritten digit classifier. Using the results of these experiments as a foundation, we propose and evaluate improvements to...

IEEE transactions on neural networks. 1997;8(5):1090-105. DOI:10.1109/72.623211 1997