Ieee transactions on neural networks文章索引

Curvature-driven smoothing: a learning algorithm for feedforward networks [0.03%] 曲率驱动的平滑处理：前馈网络的一个学习算法

C M Bishop C M Bishop

The performance of feedforward neural networks in real applications can often be improved significantly if use is made of a priori information. For interpolation problems this prior knowledge frequently includes smoothness requirements on t...

IEEE transactions on neural networks. 1993;4(5):882-4. DOI:10.1109/72.248466 1993

Encoding method for bidirectional associative memory using projection on convex sets [0.03%] 基于凸集投影的双向联想记忆编码方法

C S Leung C S Leung

The traditional encoding method of bidirectional associative memory (BAM) suggested by Kosko (1988) is based on the correlation method with which the capacity is very small. The enhanced Householder encoding algorithm (EHCA) presented here ...

IEEE transactions on neural networks. 1993;4(5):879-81. DOI:10.1109/72.248465 1993

Synthesis of a nonrecurrent associative memory model based on a nonlinear transformation in the spectral domain [0.03%] 基于频域非线性变换的非递归联想存储器模型的建立

B Hunt,M S Nadar,P Keller et al. B Hunt et al.

A new nonrecurrent associative memory model is proposed. This model is composed of a nonlinear transformation in the spectral domain followed by the association. The Moore-Penrose pseudoinverse is employed to obtain the least squares optima...

IEEE transactions on neural networks. 1993;4(5):873-8. DOI:10.1109/72.248464 1993

Performance analysis of the bidirectional associative memory and an improved model from the matched-filtering viewpoint [0.03%] 从匹配滤波的角度分析双向联想记忆及其改进模型的性能

B L Zhang,B Z Xu,C P Kwong B L Zhang

This paper discusses the bidirectional associative memory (BAM) model from the matched-filtering viewpoint and offers it a new interpretation. Our attention is focused on the problem of stability and attractivity of equilibrium states. Seve...

IEEE transactions on neural networks. 1993;4(5):864-72. DOI:10.1109/72.248463 1993

Neural networks for routing of communication networks with unreliable components [0.03%] 含不可靠元件的通信网络的路由神经网络算法研究

S L Lee,S Chang S L Lee

A new neural network model, Routron, which can handle dependent component failures of communication networks, is proposed. We prove that the proposed Routron has a stable solution. Moreover, useful upper and lower bounds for the design para...

IEEE transactions on neural networks. 1993;4(5):854-63. DOI:10.1109/72.248462 1993

Temporal winner-take-all networks: a time-based mechanism for fast selection in neural networks [0.03%] 基于时间的竞争神经网络机制

J A Barnden,K Srinivas J A Barnden

Winner-take-all (WTA) networks frequently appear in neural network models. They are primarily used for decision making and selection. As an alternative to the conventional activation-based winner-take-all mechanisms (AWTA), we present a tim...

IEEE transactions on neural networks. 1993;4(5):844-53. DOI:10.1109/72.248461 1993

Ranging through Gabor logons-a consistent, hierarchical approach [0.03%] 基于Gabor小波的层次化、一致性的纹理表征方法

C Chang,S Chatterjee C Chang

In this work, the correspondence problem in stereo vision is handled by matching two sets of dense feature vectors. Inspired by biological evidence, these feature vectors are generated by a correlation between a bank of Gabor sensors and th...

IEEE transactions on neural networks. 1993;4(5):827-43. DOI:10.1109/72.248460 1993

Symmetries and discriminability in feedforward network architectures [0.03%] 前馈网络架构中的对称性和判别性

J Shawe-Taylor J Shawe-Taylor

This paper investigates the effects of introducing symmetries into feedforward neural networks in what are termed symmetry networks. This technique allows more efficient training for problems in which we require the output of a network to b...

IEEE transactions on neural networks. 1993;4(5):816-26. DOI:10.1109/72.248459 1993

Mimic nets [0.03%] 模仿网络

G E Johnson G E Johnson

This paper introduces techniques to train feedforward nets to automate ranking and classification tasks. The techniques are denoted mimic nets since the nets can always mimic self-consistent training data. The mimic nets are constructed not...

IEEE transactions on neural networks. 1993;4(5):803-15. DOI:10.1109/72.248458 1993

Backpropagation uses prior information efficiently [0.03%] 反向传播算法高效利用先验信息

E Barnard,E C Botha E Barnard

The ability of neural net classifiers to deal with a priori information is investigated. For this purpose, backpropagation classifiers are trained with data from known distributions with variable a priori probabilities, and their performanc...

IEEE transactions on neural networks. 1993;4(5):794-802. DOI:10.1109/72.248457 1993