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
Autoassociative neural networks for image compression: a massively parallel implementation 图像压缩的自关联神经网络:大规模并行实现
Neural Networks for Signal Processing II Proceedings of the 1992 IEEE Workshop Pub Date : 1992-08-31 DOI: 10.1109/NNSP.1992.253675
A. Basso
{"title":"Autoassociative neural networks for image compression: a massively parallel implementation","authors":"A. Basso","doi":"10.1109/NNSP.1992.253675","DOIUrl":"https://doi.org/10.1109/NNSP.1992.253675","url":null,"abstract":"A massively parallel implementation on the associative string processor (ASP) machine of a neural-network-based technique for image compression is presented. Despite the linear structure of the ASP and the use of fixed arithmetic for the implementation, promising results are shown in terms of learning speed, on the order of 10/sup 9/ connections per second, and the quality of the reconstructed images.<<ETX>>","PeriodicalId":438250,"journal":{"name":"Neural Networks for Signal Processing II Proceedings of the 1992 IEEE Workshop","volume":"116 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":"124344080","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
Empirical risk optimisation: neural networks and dynamic programming 经验风险优化:神经网络和动态规划
Neural Networks for Signal Processing II Proceedings of the 1992 IEEE Workshop Pub Date : 1992-08-31 DOI: 10.1109/NNSP.1992.253701
X. Driancourt, P. Gallinari
{"title":"Empirical risk optimisation: neural networks and dynamic programming","authors":"X. Driancourt, P. Gallinari","doi":"10.1109/NNSP.1992.253701","DOIUrl":"https://doi.org/10.1109/NNSP.1992.253701","url":null,"abstract":"The authors propose a novel system for speech recognition which makes a multilayer perceptron and a dynamic programming module cooperate. It is trained through a cost function inspired by learning vector quantization which approximates the empirical average risk of misclassification. All the modules of the system are trained simultaneously through gradient backpropagation; this ensures the optimality of the system. This system has achieved very good performance for isolated-word problems and is now trained on continuous speech recognition.<<ETX>>","PeriodicalId":438250,"journal":{"name":"Neural Networks for Signal Processing II Proceedings of the 1992 IEEE Workshop","volume":"20 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":"122059523","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
Spectral representations for speech recognition by neural networks-a tutorial 神经网络语音识别的频谱表示-教程
Neural Networks for Signal Processing II Proceedings of the 1992 IEEE Workshop Pub Date : 1992-08-31 DOI: 10.1109/NNSP.1992.253691
B.H. Juang, L. Rabiner
{"title":"Spectral representations for speech recognition by neural networks-a tutorial","authors":"B.H. Juang, L. Rabiner","doi":"10.1109/NNSP.1992.253691","DOIUrl":"https://doi.org/10.1109/NNSP.1992.253691","url":null,"abstract":"Spectrum-based speech representations are discussed. Spectral representations, in order to be useful for speech recognition, need to be justified from both the computational (analytical) and the perceptual viewpoints. The authors' discussion of spectral representations, therefore, includes both the computational model and the associated measures of similarity that are appropriate for neural networks. This tutorial is intended to serve as a bridge between generic neural network classifiers and classical speech analysis for speech recognition applications. The various spectral representations discussed are intimately linked with appropriate spectral distortion measures that can be evaluated in the relevant domain of representation. The authors point out how these representations and spectral distortion measures can be applied in neural network solutions to pattern recognition problems.<<ETX>>","PeriodicalId":438250,"journal":{"name":"Neural Networks for Signal Processing II Proceedings of the 1992 IEEE Workshop","volume":"45 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":"124951093","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: 9
Interactive query learning for isolated speech recognition 孤立语音识别的交互式查询学习
Neural Networks for Signal Processing II Proceedings of the 1992 IEEE Workshop Pub Date : 1992-08-31 DOI: 10.1109/NNSP.1992.253704
J. Hwang, H. Li
{"title":"Interactive query learning for isolated speech recognition","authors":"J. Hwang, H. Li","doi":"10.1109/NNSP.1992.253704","DOIUrl":"https://doi.org/10.1109/NNSP.1992.253704","url":null,"abstract":"The authors propose an interactive query learning approach to isolated speech recognition tasks. The approach starts with training multiple 'one-net-one-class' time delay neural networks (TDNNs) based on sequences of LPC vectors. After all TDNNs are trained, initiated from each available LPC training sequence for one specific TDNN (say, class k), an improved network inversion algorithm with imposing constraint is used to generate a set of inverted LPC sequences corresponding to various output values of the corresponding TDNN. By carefully listening to synthesized speech based on the inverted LPC sequences, a conjugate pair of LPC sequences is selected from the whole set of LPC sequences; one corresponds to the acceptable speech of class k and the other corresponds to the unacceptable speech of class k. This conjugate LPC sequence pair constitutes some parts of the classification boundary associated with this class, and should be further used as the training date to refine the already trained classifier boundary. A 6% accuracy improvement was achieved when the proposed method was tested on speaker independent E-set data.<<ETX>>","PeriodicalId":438250,"journal":{"name":"Neural Networks for Signal Processing II Proceedings of the 1992 IEEE Workshop","volume":"91U 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":"128572562","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: 8
Neural network detection of small moving radar targets in an ocean environment 海洋环境下小型运动雷达目标的神经网络检测
Neural Networks for Signal Processing II Proceedings of the 1992 IEEE Workshop Pub Date : 1992-08-31 DOI: 10.1109/NNSP.1992.253682
J. Cunningham, S. Haykin
{"title":"Neural network detection of small moving radar targets in an ocean environment","authors":"J. Cunningham, S. Haykin","doi":"10.1109/NNSP.1992.253682","DOIUrl":"https://doi.org/10.1109/NNSP.1992.253682","url":null,"abstract":"Small icebergs and pieces of icebergs are virtually undetectable with conventional marine radar systems. The authors describe a detection scheme for such icebergs. The scheme uses the chirplet transform, a wavelet-inspired transform, to generate images of the Doppler-shifted radar returns from icebergs and ocean surfaces. The images are classified using a neural network trained with the backpropagation algorithm, incorporating weight sharing and optimal brain damage paradigms. The network's architecture is motivated by the known physiology of animal vision. The network design incorporates temporal information. Performance has surpassed the benchmark Fourier-based detection scheme.<<ETX>>","PeriodicalId":438250,"journal":{"name":"Neural Networks for Signal Processing II Proceedings of the 1992 IEEE Workshop","volume":"4 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":"134226270","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
Generalization in cascade-correlation networks 级联相关网络的泛化
Neural Networks for Signal Processing II Proceedings of the 1992 IEEE Workshop Pub Date : 1992-08-31 DOI: 10.1109/NNSP.1992.253707
S. Sjogaard
{"title":"Generalization in cascade-correlation networks","authors":"S. Sjogaard","doi":"10.1109/NNSP.1992.253707","DOIUrl":"https://doi.org/10.1109/NNSP.1992.253707","url":null,"abstract":"Two network construction algorithms are analyzed and compared theoretically as well as empirically. The first algorithm is the cascade correlation learning architecture proposed by S. E. Fahlman (1990), while the other algorithm is a small but striking modification of the former. Fahlman's algorithm builds multilayer feedforward networks with as many layers as the number of added hidden units, while the other algorithm operates with just one layer of hidden units. This implies that their computational capabilities and the representation of the generalizations they deal with are quite diverse, and it is demonstrated how the generalization ability of the networks generated by Fahlman's algorithm is outperformed by the networks built by the new algorithm.<<ETX>>","PeriodicalId":438250,"journal":{"name":"Neural Networks for Signal Processing II Proceedings of the 1992 IEEE Workshop","volume":"509 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":"134227662","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: 23
A neural feedforward network with a polynomial nonlinearity 具有多项式非线性的神经前馈网络
Neural Networks for Signal Processing II Proceedings of the 1992 IEEE Workshop Pub Date : 1992-08-31 DOI: 10.1109/NNSP.1992.253708
Nils Hoffmann
{"title":"A neural feedforward network with a polynomial nonlinearity","authors":"Nils Hoffmann","doi":"10.1109/NNSP.1992.253708","DOIUrl":"https://doi.org/10.1109/NNSP.1992.253708","url":null,"abstract":"A novel neural network based on the Wiener model is proposed. The network is composed of a hidden layer of preprocessing neurons followed by a polynomial nonlinearity and a linear output neuron. The author tries to solve the problem of finding an appropriate preprocessing method by using a modified backpropagation algorithm. It is shown by the use of calculation trees that the proposed approach is simple to implement, and that the computational complexity is not much larger than for the alternative method of using PCA to determine the weights in the preprocessing network. A simulation is given which indicates superior performance of the proposed network compared to the PCA network.<<ETX>>","PeriodicalId":438250,"journal":{"name":"Neural Networks for Signal Processing II Proceedings of the 1992 IEEE Workshop","volume":"108 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":"132369189","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: 2
Hierarchical perceptron (HiPer) networks for signal/image classifications 用于信号/图像分类的层次感知器(HiPer)网络
Neural Networks for Signal Processing II Proceedings of the 1992 IEEE Workshop Pub Date : 1992-08-31 DOI: 10.1109/NNSP.1992.253686
S. Kung, J. Taur
{"title":"Hierarchical perceptron (HiPer) networks for signal/image classifications","authors":"S. Kung, J. Taur","doi":"10.1109/NNSP.1992.253686","DOIUrl":"https://doi.org/10.1109/NNSP.1992.253686","url":null,"abstract":"A new class of decision-based neural networks (DBNNs) is introduced. These networks combine the perceptron-like learning rule with a hierarchical nonlinear network structure and are called HiPer nets. Two HiPer net structures are proposed: hidden-node and subcluster structures. The authors explore several variants of HiPer nets based on the different hierarchical structures and basis functions and then examine the relationships between HiPer nets and other DBNNs, e.g., perceptron and LVQ. Based on the simulation performance comparison, the HiPer nets appear to be very effective for many signal/image classification applications, including texture classification, OCR (optical character recognition), and ECG (electrocardiography).<<ETX>>","PeriodicalId":438250,"journal":{"name":"Neural Networks for Signal Processing II Proceedings of the 1992 IEEE Workshop","volume":"81 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":"114901712","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
Supervised learning on large redundant training sets 大型冗余训练集上的监督学习
Neural Networks for Signal Processing II Proceedings of the 1992 IEEE Workshop Pub Date : 1992-08-31 DOI: 10.1109/NNSP.1992.253705
M. F. Møller
{"title":"Supervised learning on large redundant training sets","authors":"M. F. Møller","doi":"10.1109/NNSP.1992.253705","DOIUrl":"https://doi.org/10.1109/NNSP.1992.253705","url":null,"abstract":"A novel algorithm combining the good properties of offline and online algorithms is introduced. The efficiency of supervised learning algorithms on small-scale problems does not necessarily scale up to large-scale problems. The redundancy of large training sets is reflected as redundancy gradient vectors in the network. Accumulating these gradient vectors implies redundant computations. In order to avoid these redundant computations a learning algorithm has to be able to update weights independently of the size of the training set. The stochastic learning algorithm proposed, the stochastic scaled conjugate gradient (SSCG) algorithm, has this property. Experimentally, it is shown that SSCG converges faster than the online backpropagation algorithm on the nettalk problem.<<ETX>>","PeriodicalId":438250,"journal":{"name":"Neural Networks for Signal Processing II Proceedings of the 1992 IEEE Workshop","volume":"109 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":"117288032","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
Nonlinear system identification using multilayer perceptrons with locally recurrent synaptic structure 具有局部递归突触结构的多层感知器非线性系统辨识
Neural Networks for Signal Processing II Proceedings of the 1992 IEEE Workshop Pub Date : 1992-08-31 DOI: 10.1109/NNSP.1992.253668
A. Back, A. Tsoi
{"title":"Nonlinear system identification using multilayer perceptrons with locally recurrent synaptic structure","authors":"A. Back, A. Tsoi","doi":"10.1109/NNSP.1992.253668","DOIUrl":"https://doi.org/10.1109/NNSP.1992.253668","url":null,"abstract":"It is proved that a multilayer perceptron (MLP) with infinite impulse response (IIR) synapses can represent a class of nonlinear block-oriented systems. This includes the well-known Wiener, Hammerstein, and cascade or sandwich systems. Previous methods used to model these systems such as the Volterra series representation are known to be extremely inefficient, and so the IIR MLP represents an effective method of modeling block-oriented nonlinear systems. This was demonstrated by simulations on two models within the class. The significance of the IIR MLP is that it demonstrates that a useful range of systems can be modeled by a network architecture based on the MLP and adaptive linear filters.<<ETX>>","PeriodicalId":438250,"journal":{"name":"Neural Networks for Signal Processing II Proceedings of the 1992 IEEE Workshop","volume":"47 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":"127864819","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: 9
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