Stability and statistical properties of second-order bidirectional associative memory [0.03%]
二阶互联系忆网络的稳定性及其统计特性研究
C S Leung,L W Chan,E K Lai
C S Leung
In this paper, a bidirectional associative memory (BAM) model with second-order connections, namely second-order bidirectional associative memory (SOBAM), is first reviewed. The stability and statistical properties of the SOBAM are then exa...
Topology preservation in self-organizing feature maps: exact definition and measurement [0.03%]
自组织特征映射中拓扑保持性的精确定义及度量方法研究
T Villmann,R Der,M Herrmann et al.
T Villmann et al.
The neighborhood preservation of self-organizing feature maps like the Kohonen map is an important property which is exploited in many applications. However, if a dimensional conflict arises this property is lost. Various qualitative and qu...
Capabilities of a four-layered feedforward neural network: four layers versus three [0.03%]
四层前向神经网络的能力：四层对三层
S Tamura,M Tateishi
S Tamura
Neural-network theorems state that only when there are infinitely many hidden units is a four-layered feedforward neural network equivalent to a three-layered feedforward neural network. In actual applications, however, the use of infinitel...
Cascade ARTMAP: integrating neural computation and symbolic knowledge processing [0.03%]
级联ARTMAP：集成了神经计算与符号知识处理
A H Tan
A H Tan
This paper introduces a hybrid system termed cascade adaptive resonance theory mapping (ARTMAP) that incorporates symbolic knowledge into neural-network learning and recognition. Cascade ARTMAP, a generalization of fuzzy ARTMAP, represents ...
Q Zhang
Q Zhang
Wavelet networks are a class of neural networks consisting of wavelets. In this paper, algorithms for wavelet network construction are proposed for the purpose of nonparametric regression estimation. Particular attentions are paid to sparse...
H U Bauer,T Villmann
H U Bauer
Neural maps project data from an input space onto a neuron position in a (often lower dimensional) output space grid in a neighborhood preserving way, with neighboring neurons in the output space responding to neighboring data points in the...
Unsupervised query-based learning of neural networks using selective-attention and self-regulation [0.03%]
基于无监督查询的利用选择性注意和自我调节的神经网络学习方法研究
R I Chang,P Y Hsiao
R I Chang
Query-based learning (QBL) has been introduced for training a supervised network model with additional queried samples. Experiments demonstrated that the classification accuracy is further increased. Although QBL has been successfully appli...
Robust speech recognition based on joint model and feature space optimization of hidden Markov models [0.03%]
基于隐马尔可夫模型联合模型及特征空间优化的鲁棒性语音识别
S Moon,J N Hwang
S Moon
The hidden Markov model (HMM) inversion algorithm, based on either the gradient search or the Baum-Welch reestimation of input speech features, is proposed and applied to the robust speech recognition tasks under general types of mismatch c...
Adaptive color segmentation-a comparison of neural and statistical methods [0.03%]
自适应颜色分割-神经方法和统计方法的比较研究
E Littmann,H Ritter
E Littmann
With the availability of more powerful computers it is nowadays possible to perform pixel based operations on real camera images even in the full color space. New adaptive classification tools like neural networks make it possible to develo...