发布求助
文献互助 智能选刊 最新文献

Neural Networks for Signal Processing II Proceedings of the 1992 IEEE Workshop最新文献

筛选
英文 中文
Chaotic signal emulation using a recurrent time delay neural network 混沌信号的递归时延神经网络仿真
Neural Networks for Signal Processing II Proceedings of the 1992 IEEE Workshop Pub Date : 1992-08-31 DOI: 10.1109/NNSP.1992.253667
M. Davenport, S. P. Day
{"title":"Chaotic signal emulation using a recurrent time delay neural network","authors":"M. Davenport, S. P. Day","doi":"10.1109/NNSP.1992.253667","DOIUrl":"https://doi.org/10.1109/NNSP.1992.253667","url":null,"abstract":"The authors describe a method for training a dispersive neural network to imitate a chaotic signal without using any knowledge of how the signal was generated. In a dispersive network, each connection has both an adaptable time delay and an adaptable weight. The network was first trained as a feedforward signal predictor and then connected recurrently for signal synthesis. The authors evaluate the performance of a network with twenty hidden nodes, using the Mackey-Glass (1977) chaotic time series as a training signal, and then compare it to a similar network without internal time delays. The fidelity of the synthesized signal is investigated for progressively longer training times, and for networks trained with and without momentum.<<ETX>>","PeriodicalId":438250,"journal":{"name":"Neural Networks for Signal Processing II Proceedings of the 1992 IEEE Workshop","volume":"2 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1992-08-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128729547","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 3
On the complexity of neural networks with sigmoidal units 具有s型单元的神经网络的复杂性
Neural Networks for Signal Processing II Proceedings of the 1992 IEEE Workshop Pub Date : 1992-08-31 DOI: 10.1109/NNSP.1992.253711
Kai-Yeung Siu, V. Roychowdhury, T. Kailath
{"title":"On the complexity of neural networks with sigmoidal units","authors":"Kai-Yeung Siu, V. Roychowdhury, T. Kailath","doi":"10.1109/NNSP.1992.253711","DOIUrl":"https://doi.org/10.1109/NNSP.1992.253711","url":null,"abstract":"Novel techniques based on classical tools such as rational approximation and harmonic analysis are developed to study the computational properties of neural networks. Using such techniques, one can characterize the class of function whose complexity is almost the same among various models of neural networks with feedforward structures. As a consequence of this characterization, for example, it is proved that any depth-(d+1) network of sigmoidal units computing the parity function of n inputs must have Omega (dn/sup 1/d- in /) units, for any fixed in >0. This lower bound is almost tight since one can compute the parity function with O(dn/sup 1/d/) sigmoidal units in a depth-(d+1) network. The techniques also generalize to networks whose elements can be approximated by piecewise low degree rational functions.<<ETX>>","PeriodicalId":438250,"journal":{"name":"Neural Networks for Signal Processing II Proceedings of the 1992 IEEE Workshop","volume":"106 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1992-08-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134126495","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 5
Image recognition using a neural network 使用神经网络的图像识别
Neural Networks for Signal Processing II Proceedings of the 1992 IEEE Workshop Pub Date : 1992-08-31 DOI: 10.1109/NNSP.1992.253680
Ken-Chung Ho, Bin-Chang Chieu
{"title":"Image recognition using a neural network","authors":"Ken-Chung Ho, Bin-Chang Chieu","doi":"10.1109/NNSP.1992.253680","DOIUrl":"https://doi.org/10.1109/NNSP.1992.253680","url":null,"abstract":"A new type of feedforward neural network for recognition of MRF (Markov random field) images is presented. The proposed forward and backward networks are essentially generalizations of the forward and backward procedures in backpropagation training for general feedforward networks. Due to the feedforward structure of the networks, they are recurrent for homogeneous MRF images and easy to implement. Because of the use of the maximum-likelihood criterion, this approach always performs well if all classes of images are equally likely. Basically, the proposed approach takes advantage of the feedforward neural networks and, by the joint probability, solves two basic problems in MRF modeling: how to measure a Gibbs distribution and how to estimate the Gibbs parameters from clean and noisy MRF samples.<<ETX>>","PeriodicalId":438250,"journal":{"name":"Neural Networks for Signal Processing II Proceedings of the 1992 IEEE Workshop","volume":"23 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1992-08-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127298255","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
Robust identification of human face using mosaic pattern and BPN 基于马赛克图案和bp神经网络的人脸鲁棒识别
Neural Networks for Signal Processing II Proceedings of the 1992 IEEE Workshop Pub Date : 1992-08-31 DOI: 10.1109/NNSP.1992.253683
M. Kosugi
{"title":"Robust identification of human face using mosaic pattern and BPN","authors":"M. Kosugi","doi":"10.1109/NNSP.1992.253683","DOIUrl":"https://doi.org/10.1109/NNSP.1992.253683","url":null,"abstract":"The backpropagation network (BPN) is applied to human face recognition. A mosaic pattern transformed from the central part of a human face image is put into the BPN for personal identification. This combination succeeds in recognition of hundreds of people with robustness not only for defocused or noisy images but also for images of different face expressions or different ages. Hidden units of the BPN extract peculiar and delicate features of the face, which cannot be obtained from existing statistical methods. A few hidden units can especially select only men or women. Moreover, a BPN with an additional unit for processing unfamiliar faces is proposed.<<ETX>>","PeriodicalId":438250,"journal":{"name":"Neural Networks for Signal Processing II Proceedings of the 1992 IEEE Workshop","volume":"80 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1992-08-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121566225","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 14
Compression of subband-filtered images via neural networks 基于神经网络的亚带滤波图像压缩
Neural Networks for Signal Processing II Proceedings of the 1992 IEEE Workshop Pub Date : 1992-08-31 DOI: 10.1109/NNSP.1992.253674
Sergio Carrato, S. Marsi
{"title":"Compression of subband-filtered images via neural networks","authors":"Sergio Carrato, S. Marsi","doi":"10.1109/NNSP.1992.253674","DOIUrl":"https://doi.org/10.1109/NNSP.1992.253674","url":null,"abstract":"A novel architecture for image compression is proposed, which is based on a suitable combination of subband filtering and linear neural networks. This combination permits efficient coding, together with the advantages of the neural-network-based approach. The architecture is described, and results of simulations are presented. The architecture is shown to perform well, notwithstanding the reduced complexity of the approach. The structure is highly parallel, so that high computation rates are possible; this property can be useful if sequences of images are to be compressed.<<ETX>>","PeriodicalId":438250,"journal":{"name":"Neural Networks for Signal Processing II Proceedings of the 1992 IEEE Workshop","volume":"24 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1992-08-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122783088","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 1
Self-structuring hidden control neural models 自结构隐藏控制神经模型
Neural Networks for Signal Processing II Proceedings of the 1992 IEEE Workshop Pub Date : 1992-08-31 DOI: 10.1109/NNSP.1992.253698
H. Sørensen, U. Hartmann
{"title":"Self-structuring hidden control neural models","authors":"H. Sørensen, U. Hartmann","doi":"10.1109/NNSP.1992.253698","DOIUrl":"https://doi.org/10.1109/NNSP.1992.253698","url":null,"abstract":"The authors propose a self-structuring hidden control (SHC) neural model for pattern recognition which establishes a near-optimal architecture during training. A significant network architecture reduction in terms of the number of hidden processing elements (PEs) is typically achieved. The SHC model combines self-structuring architecture generation with nonlinear prediction and hidden Markov modelling. The authors present a theorem for self-structuring neural models stating that these models are universal approximators and thus relevant to real-world pattern recognition. Using SHC models containing as few as five hidden PEs each for an isolated word recognition task resulted in a recognition rate of 98.4%. SHC models can also be applied to continuous speech recognition.<<ETX>>","PeriodicalId":438250,"journal":{"name":"Neural Networks for Signal Processing II Proceedings of the 1992 IEEE Workshop","volume":"48 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1992-08-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116225534","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
A partial analysis of stochastic convergence in a generalized two-layer perceptron with backpropagation learning 具有反向传播学习的广义两层感知器随机收敛性的部分分析
Neural Networks for Signal Processing II Proceedings of the 1992 IEEE Workshop Pub Date : 1992-08-31 DOI: 10.1109/NNSP.1992.253660
J. L. Vaughn, N. Bershad, J. Shynk
{"title":"A partial analysis of stochastic convergence in a generalized two-layer perceptron with backpropagation learning","authors":"J. L. Vaughn, N. Bershad, J. Shynk","doi":"10.1109/NNSP.1992.253660","DOIUrl":"https://doi.org/10.1109/NNSP.1992.253660","url":null,"abstract":"The authors study the stationary points of a two-layer perceptron which attempts to identify the parameters of a specific stochastic nonlinear system. The training sequence is modeled as the output of the nonlinear system, with an input comprising an independent sequence of zero mean Gaussian vectors with independent components. The training rule is a limiting case of backpropagation (to simplify the analysis). Equations are given which define the stationary points of the algorithm for an arbitrary output nonlinearity g(x). The solutions to these equations for the outer layer show that, for a continuous g(x), there is a unique solution for the outer layer weights for any given set of fixed hidden layer weights. These solutions do not necessarily yield zero error. However, if the hidden layer weights are also trained, the unique solution for zero error requires that the parameters of the two-layer perceptron exactly match that of the nonlinear system.<<ETX>>","PeriodicalId":438250,"journal":{"name":"Neural Networks for Signal Processing II Proceedings of the 1992 IEEE Workshop","volume":"17 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1992-08-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125226702","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
Noise density estimation using neural networks 基于神经网络的噪声密度估计
Neural Networks for Signal Processing II Proceedings of the 1992 IEEE Workshop Pub Date : 1992-08-31 DOI: 10.1109/NNSP.1992.253664
M. Musavi, D. Hummels, A. Laffely, S. Kennedy
{"title":"Noise density estimation using neural networks","authors":"M. Musavi, D. Hummels, A. Laffely, S. Kennedy","doi":"10.1109/NNSP.1992.253664","DOIUrl":"https://doi.org/10.1109/NNSP.1992.253664","url":null,"abstract":"A neural network for estimation of unknown noise densities and their gradients is presented. The network structure is similar to a radial basis function. The learning rule is, however, different and has an unsupervised nature that ensures a valid probability density. The algorithm is fast and provides good estimates of noise densities. One and two dimensional examples are reported.<<ETX>>","PeriodicalId":438250,"journal":{"name":"Neural Networks for Signal Processing II Proceedings of the 1992 IEEE Workshop","volume":"19 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1992-08-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130248332","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 4
Learning rate schedules for faster stochastic gradient search 更快的随机梯度搜索的学习率调度
Neural Networks for Signal Processing II Proceedings of the 1992 IEEE Workshop Pub Date : 1992-08-31 DOI: 10.1109/NNSP.1992.253713
C. Darken, Joseph T. Chang, J. Moody
{"title":"Learning rate schedules for faster stochastic gradient search","authors":"C. Darken, Joseph T. Chang, J. Moody","doi":"10.1109/NNSP.1992.253713","DOIUrl":"https://doi.org/10.1109/NNSP.1992.253713","url":null,"abstract":"The authors propose a new methodology for creating the first automatically adapting learning rates that achieve the optimal rate of convergence for stochastic gradient descent. Empirical tests agree with theoretical expectations that drift can be used to determine whether the crucial parameter c is large enough. Using this statistic, it will be possible to produce the first adaptive learning rates which converge at optimal speed.<<ETX>>","PeriodicalId":438250,"journal":{"name":"Neural Networks for Signal Processing II Proceedings of the 1992 IEEE Workshop","volume":"IA-13 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1992-08-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126556785","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 219
On the identification of phonemes using acoustic-phonetic features derived by a self-organising neural network 利用自组织神经网络衍生的声学-语音特征识别音素
Neural Networks for Signal Processing II Proceedings of the 1992 IEEE Workshop Pub Date : 1992-08-31 DOI: 10.1109/NNSP.1992.253688
P. Dalsgaard, O. Andersen, R. Jørgensen
{"title":"On the identification of phonemes using acoustic-phonetic features derived by a self-organising neural network","authors":"P. Dalsgaard, O. Andersen, R. Jørgensen","doi":"10.1109/NNSP.1992.253688","DOIUrl":"https://doi.org/10.1109/NNSP.1992.253688","url":null,"abstract":"A self-organizing neural network (SONN) is subjected to a training and calibration process using continuous speech spoken by three talkers. The aim of this process is to establish a system which is able to transform speech frame cepstrum vectors into vectors of continuous valued acoustic-phonetic features. The calibration process also involves a stage where each neuron of the SONN is assigned a vector defining the links between speech technology and articulatory phonetic concepts. The validity of the transformation approach is shown by applying a speech test corpus to the SONN transformation. The main results of the established transformation technique are given in a number of histograms by which it is shown that the computed acoustic-phonetic feature values to a large extent are in accordance with the phonological specifications used in the feature transformation. The histograms are further used to demonstrate the ability of the acoustic-phonetic features to identify individual phonemes and to discriminate between vocalic and consonantal phonemes.<<ETX>>","PeriodicalId":438250,"journal":{"name":"Neural Networks for Signal Processing II Proceedings of the 1992 IEEE Workshop","volume":"30 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1992-08-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126793838","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
首页 上一页 下一页 尾页
0
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整，为了账户安全，请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
现在去查看 取消
×
提示
确定
请完成安全验证×
相关产品
×
本文献相关产品
联系我们：info@booksci.cn Book学术提供免费学术资源搜索服务，方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号：481959085
Book学术官方微信