Ieee transactions on neural networks文章索引

Two coding strategies for bidirectional associative memory [0.03%] 双向联想记忆的两种编码策略

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

Enhancements of the encoding strategy of a discrete bidirectional associative memory (BAM) reported by B. Kosko (1987) are presented. There are two major concepts in this work: multiple training, which can be guaranteed to achieve recall of...

IEEE transactions on neural networks. 1990;1(1):81-92. DOI:10.1109/72.80207 1990

Sensitivity of feedforward neural networks to weight errors [0.03%] 前馈神经网络的权重误差敏感性

M Stevenson,R Winter,B Widrow M Stevenson

An analysis is made of the sensitivity of feedforward layered networks of Adaline elements (threshold logic units) to weight errors. An approximation is derived which expresses the probability of error for an output neuron of a large networ...

IEEE transactions on neural networks. 1990;1(1):71-80. DOI:10.1109/72.80206 1990

Model-free distributed learning [0.03%] 无模型分布式学习

A Dembo,T Kailath A Dembo

Model-free learning for synchronous and asynchronous quasi-static networks is presented. The network weights are continuously perturbed, while the time-varying performance index is measured and correlated with the perturbation signals; the ...

IEEE transactions on neural networks. 1990;1(1):58-70. DOI:10.1109/72.80205 1990

Unsupervised learning in noise [0.03%] 含噪情况下的无监督学习

B Kosko B Kosko

A new hybrid learning law, the differential competitive law, which uses the neuronal signal velocity as a local unsupervised reinforcement mechanism, is introduced, and its coding and stability behavior in feedforward and feedback networks ...

IEEE transactions on neural networks. 1990;1(1):44-57. DOI:10.1109/72.80204 1990

Survey of neural network technology for automatic target recognition [0.03%] 自动目标识别的神经网络技术综述

M W Roth M W Roth

A review is presented of ATR (automatic target recognition), and some of the highlights of neural network technology developments that have the potential for making a significant impact on ATR are presented. In particular, neural network te...

IEEE transactions on neural networks. 1990;1(1):28-43. DOI:10.1109/72.80203 1990

Identification and control of dynamical systems using neural networks [0.03%] 利用神经网络进行动力系统识别与控制

K S Narendra,K Parthasarathy K S Narendra

It is demonstrated that neural networks can be used effectively for the identification and control of nonlinear dynamical systems. The emphasis is on models for both identification and control. Static and dynamic backpropagation methods for...

IEEE transactions on neural networks. 1990;1(1):4-27. DOI:10.1109/72.80202 1990

Training a network with ternary weights using the CHIR algorithm [0.03%] 基于CHIR算法的ternary权重网络训练方法

S Abramson,D Saad,E Marom S Abramson

A modification of the binary weight CHIR algorithm is presented, whereby a zero state is added to the possible binary weight states. This method allows solutions with reduced connectivity to be obtained, by offering disconnections in additi...

IEEE transactions on neural networks. 1993;4(6):997-1000. DOI:10.1109/72.286901 1993

Application of Hopfield network to saccades [0.03%] Hopfield网络在扫视中的应用研究

T Washizawa T Washizawa

Human eye movement mechanisms (saccades) are very useful for scene analysis, including object representation and pattern recognition. A Hopfield neural network for emulating saccades is proposed. The network uses an energy function that inc...

IEEE transactions on neural networks. 1993;4(6):995-7. DOI:10.1109/72.286896 1993

Empirical results of using back-propagation neural networks to separate single echoes from multiple echoes [0.03%] 用反馈分布神经网络从多个回波中分离单个回波的实验结果

W Chang,B Bosworth,G C Carter W Chang

Empirical results illustrate the pitfalls of applying an artificial neural network (ANN) to classification of underwater active sonar returns. During training, a back-propagation ANN classifier learns to recognize two classes of reflected a...

IEEE transactions on neural networks. 1993;4(6):993-5. DOI:10.1109/72.286895 1993

A combinatorial approach to understanding perceptron capabilities [0.03%] 组合方法解读感知器能力上限

G J Gibson G J Gibson

This work investigates the classification capabilities of perceptrons which incorporate a single hidden layer of nodes from a theoretical viewpoint. In particular, the question of determining whether a given set can be realized as the decis...

IEEE transactions on neural networks. 1993;4(6):989-92. DOI:10.1109/72.286894 1993