发布求助
文献互助 智能选刊 最新文献

Neural Networks for Signal Processing Proceedings of the 1991 IEEE Workshop最新文献

筛选
英文 中文
Experiments with temporal resolution for continuous speech recognition with multi-layer perceptrons 多层感知器连续语音识别的时间分辨率实验
Neural Networks for Signal Processing Proceedings of the 1991 IEEE Workshop Pub Date : 1991-09-30 DOI: 10.1109/NNSP.1991.239501
N. Morgan, Chuck Wooters, H. Hermansky
{"title":"Experiments with temporal resolution for continuous speech recognition with multi-layer perceptrons","authors":"N. Morgan, Chuck Wooters, H. Hermansky","doi":"10.1109/NNSP.1991.239501","DOIUrl":"https://doi.org/10.1109/NNSP.1991.239501","url":null,"abstract":"Previous work by the authors focused on the integration of multilayer perceptrons (MLP) into hidden Markov models (HMM) and on the use of perceptual linear prediction (PLP) parameters for the feature inputs to such nets. The system uses the Viterbi algorithm for temporal alignment. This algorithm is a simple and optimal procedure, but it necessitates a frame-based analysis in which all features have the same implicit time constants. The authors provide a range of temporal/spectral resolution choices to a frame-based system by using a layered network to incorporate this information for phonetic discrimination. They have performed experiments in which they expanded their PLP analysis to include short analysis windows, and in which they trained phonetic classification networks to incorporate this added information. They hypothesized that classification scores would improve, especially for short-duration phonemes. These experiments did not yield the expected improvement.<<ETX>>","PeriodicalId":354832,"journal":{"name":"Neural Networks for Signal Processing Proceedings of the 1991 IEEE Workshop","volume":"256 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1991-09-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122740362","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
Multiply descent cost competitive neural networks with cooperation and categorization 具有合作和分类的多重下降成本竞争神经网络
Neural Networks for Signal Processing Proceedings of the 1991 IEEE Workshop Pub Date : 1991-09-30 DOI: 10.1109/NNSP.1991.239527
Y. Matsuyama
{"title":"Multiply descent cost competitive neural networks with cooperation and categorization","authors":"Y. Matsuyama","doi":"10.1109/NNSP.1991.239527","DOIUrl":"https://doi.org/10.1109/NNSP.1991.239527","url":null,"abstract":"Generalized competitive learning algorithms are described. These algorithms comprise competition handicaps, cooperation and multiply descent cost property. Applications are made on single processing and combinatorial optimizations. Parallel computation of the algorithms presented is discussed.<<ETX>>","PeriodicalId":354832,"journal":{"name":"Neural Networks for Signal Processing Proceedings of the 1991 IEEE Workshop","volume":"8 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1991-09-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123261923","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
Recursive neural networks for signal processing and control 用于信号处理和控制的递归神经网络
Neural Networks for Signal Processing Proceedings of the 1991 IEEE Workshop Pub Date : 1991-09-30 DOI: 10.1109/NNSP.1991.239489
D. Hush, C. Abdallah, B. Horne
{"title":"Recursive neural networks for signal processing and control","authors":"D. Hush, C. Abdallah, B. Horne","doi":"10.1109/NNSP.1991.239489","DOIUrl":"https://doi.org/10.1109/NNSP.1991.239489","url":null,"abstract":"The authors describe a special type of dynamic neural network called the recursive neural network (RNN). The RNN is a single-input single-output nonlinear dynamical system with a nonrecursive subnet and two recursive subnets arranged in the configuration shown. The authors describe the architecture of the RNN, present a learning algorithm for the network, and provide some examples of its use.<<ETX>>","PeriodicalId":354832,"journal":{"name":"Neural Networks for Signal Processing Proceedings of the 1991 IEEE Workshop","volume":"124 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1991-09-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114655693","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: 6
Vector quantisation with a codebook-excited neural network 用码本激励的神经网络进行矢量量化
Neural Networks for Signal Processing Proceedings of the 1991 IEEE Workshop Pub Date : 1991-09-30 DOI: 10.1109/NNSP.1991.239498
L. Wu, F. Fallside
{"title":"Vector quantisation with a codebook-excited neural network","authors":"L. Wu, F. Fallside","doi":"10.1109/NNSP.1991.239498","DOIUrl":"https://doi.org/10.1109/NNSP.1991.239498","url":null,"abstract":"An alternative model named a codebook-excited neural network has been proposed for source coding or vector quantisation. Two advantages of this model are that the memory information between source frames can easily be taken into account by recurrent connections and that the number of network connections is independent of the transmission rate. The simulations have also shown its good quantisation performance. The codebook-excited neural network is applicable with any distortion measure. For a zero-mean, unit variance, memoryless Gaussian source and a squared-error measure, a 1 bit/sample two-dimensional quantiser with a codebook-excited feedforward neural network is found to always escape from the local minima and converge to the best one of the three local minima which are known to exist in the vector quantiser designed using the LBG algorithm. Moreover, due to its conformal mapping characteristic, the codebook-excited neural network can be applied to designing the vector quantiser with any required structural form on its codevectors.<<ETX>>","PeriodicalId":354832,"journal":{"name":"Neural Networks for Signal Processing Proceedings of the 1991 IEEE Workshop","volume":"18 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1991-09-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114402365","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
Design of a digital VLSI neuroprocessor for signal and image processing 用于信号和图像处理的数字VLSI神经处理器的设计
Neural Networks for Signal Processing Proceedings of the 1991 IEEE Workshop Pub Date : 1991-09-30 DOI: 10.1109/NNSP.1991.239480
C. Chang, B. Sheu
{"title":"Design of a digital VLSI neuroprocessor for signal and image processing","authors":"C. Chang, B. Sheu","doi":"10.1109/NNSP.1991.239480","DOIUrl":"https://doi.org/10.1109/NNSP.1991.239480","url":null,"abstract":"An efficient processing element for data/image processing has been designed. Detailed communication networks, instruction sets and circuit blocks are created for ring-connected and mesh-connected systolic arrays for the retrieving and learning phases of the neural network operations. 800 processing elements can be implemented in 3.75 cm*3.75 cm chip by using the 0.5 mu m CMOS technology from TRW, Inc. This digital neuroprocessor can also be extended to support fuzzy logic inference.<<ETX>>","PeriodicalId":354832,"journal":{"name":"Neural Networks for Signal Processing Proceedings of the 1991 IEEE Workshop","volume":"29 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1991-09-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124436621","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
Ordered neural maps and their applications to data compression 有序神经映射及其在数据压缩中的应用
Neural Networks for Signal Processing Proceedings of the 1991 IEEE Workshop Pub Date : 1991-09-30 DOI: 10.1109/NNSP.1991.239487
E. Riskin, L. Atlas, S. Lay
{"title":"Ordered neural maps and their applications to data compression","authors":"E. Riskin, L. Atlas, S. Lay","doi":"10.1109/NNSP.1991.239487","DOIUrl":"https://doi.org/10.1109/NNSP.1991.239487","url":null,"abstract":"The implicit ordering in scalar quantization is used to substantiate the need for explicit ordering in vector quantization and the ordering of Kohonen's neural net vector quantizer is shown to provide a multidimensional analog to this scalar quantization ordering. Ordered vector quantization, using Kohonen's neural net, was successfully applied to image coding and was then shown to be advantageous for progressive transmission. In particular, the intermediate images had a signal-to-noise ratio that was quite close to a standard tree-structured vector quantizer, while the final full-fidelity image from the neural net vector quantizer was superior to the tree-structured vector quantizer. Subsidiary results include a new definition of index of disorder which was empirically found to correlate strongly with the progressive reduction of image signal-to-noise ratio and a hybrid neural net-generalized Lloyd training algorithm which has a high final image signal-to-noise ratio while still maintaining ordering.<<ETX>>","PeriodicalId":354832,"journal":{"name":"Neural Networks for Signal Processing Proceedings of the 1991 IEEE Workshop","volume":"16 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1991-09-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115365532","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: 18
A surface reconstruction neural network for absolute orientation problems 面向绝对定向问题的曲面重构神经网络
Neural Networks for Signal Processing Proceedings of the 1991 IEEE Workshop Pub Date : 1991-09-30 DOI: 10.1109/NNSP.1991.239490
J. Hwang, H. Li
{"title":"A surface reconstruction neural network for absolute orientation problems","authors":"J. Hwang, H. Li","doi":"10.1109/NNSP.1991.239490","DOIUrl":"https://doi.org/10.1109/NNSP.1991.239490","url":null,"abstract":"The authors propose a neural network for representation and reconstruction of 2-D curves or 3-D surfaces of complex objects with application to absolute orientation problems of rigid bodies. The surface reconstruction network is trained by a set of roots (the points on the curve or the surface of the object) via forming a very steep cliff between the exterior and interior of the surface, with the training root points lying in the middle of the steep cliff. The Levenberg-Marquardt version of Gauss Newton optimization algorithm was used in the backpropagation learning to overcome the problem of local minima and to speed up the convergence of learning. This representation is then used to estimate the similarity transform parameters (rotation, translation, and scaling), frequently encountered in the absolute orientation problems of rigid bodies.<<ETX>>","PeriodicalId":354832,"journal":{"name":"Neural Networks for Signal Processing Proceedings of the 1991 IEEE Workshop","volume":"23 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1991-09-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121146390","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: 6
Lithofacies determination from wire-line log data using a distributed neural network 利用分布式神经网络从电缆测井数据确定岩相
Neural Networks for Signal Processing Proceedings of the 1991 IEEE Workshop Pub Date : 1991-09-30 DOI: 10.1109/NNSP.1991.239493
M. Smith, N. Carmichael, I. Reid, C. Bruce
{"title":"Lithofacies determination from wire-line log data using a distributed neural network","authors":"M. Smith, N. Carmichael, I. Reid, C. Bruce","doi":"10.1109/NNSP.1991.239493","DOIUrl":"https://doi.org/10.1109/NNSP.1991.239493","url":null,"abstract":"A distributed neural network, running on a large transputer-based parallel computer, was trained to identify the presence of the main lithographical facies types in a particular oil well, using only the readings obtained by a log probe. The resulting trained network was then used to analyse a variety of other wells, and showed only a small decrease in accuracy of identification. Geologists classify well structures using rock and fossil samples in addition to the log data that was given to the network. Results are given here for the accuracy with which the learned network agreed with analyses performed by geologists. The study was then extended into two more areas, firstly to investigate the network's success in predicting physical attributes of the rocks, e.g. porosity and permeability, and secondly to investigate the ability of similar networks to isolate particular geological features.<<ETX>>","PeriodicalId":354832,"journal":{"name":"Neural Networks for Signal Processing Proceedings of the 1991 IEEE Workshop","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1991-09-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127122093","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
Fingerprint recognition using neural network 基于神经网络的指纹识别
Neural Networks for Signal Processing Proceedings of the 1991 IEEE Workshop Pub Date : 1991-09-30 DOI: 10.1109/NNSP.1991.239519
W. Leung, S. Leung, W. H. Lau, A. Luk
{"title":"Fingerprint recognition using neural network","authors":"W. Leung, S. Leung, W. H. Lau, A. Luk","doi":"10.1109/NNSP.1991.239519","DOIUrl":"https://doi.org/10.1109/NNSP.1991.239519","url":null,"abstract":"The authors describe a neural network based approach for automated fingerprint recognition. Minutiae are extracted from the fingerprint image via a multilayer perceptron (MLP) classifier with one hidden layer. The backpropagation learning technique is used for its training. Selected features are represented in a special way such that they are simultaneously invariant under shift, rotation and scaling. Simulation results are obtained with good detection ratio and low failure rate. The proposed method is found to be reliable for a system with a small set of fingerprint data.<<ETX>>","PeriodicalId":354832,"journal":{"name":"Neural Networks for Signal Processing Proceedings of the 1991 IEEE Workshop","volume":"9 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1991-09-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125196084","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: 69
Pattern recognition properties of neural networks 神经网络的模式识别特性
Neural Networks for Signal Processing Proceedings of the 1991 IEEE Workshop Pub Date : 1991-09-30 DOI: 10.1109/NNSP.1991.239524
J. Makhoul
{"title":"Pattern recognition properties of neural networks","authors":"J. Makhoul","doi":"10.1109/NNSP.1991.239524","DOIUrl":"https://doi.org/10.1109/NNSP.1991.239524","url":null,"abstract":"Artificial neural networks have been applied largely to solving pattern recognition problems. The authors point out that a firm understanding of the statistical properties of neural nets is important for using them in an effective manner for pattern recognition problems. The author gives an overview of pattern recognition properties for feedforward neural nets, with emphasis on two topics: partitioning of the input space into classes and the estimation of posterior probabilities for each of the classes.<<ETX>>","PeriodicalId":354832,"journal":{"name":"Neural Networks for Signal Processing Proceedings of the 1991 IEEE Workshop","volume":"29 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1991-09-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133113141","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: 51
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：604180095
Book学术官方微信