发布求助
文献互助 智能选刊 最新文献

Proceedings of 1995 IEEE Workshop on Neural Networks for Signal Processing最新文献

筛选
英文 中文
Level crossing time interval circuit for micro-power analog VLSI auditory processing 用于微功率模拟VLSI听觉处理的水平交叉时间间隔电路
Proceedings of 1995 IEEE Workshop on Neural Networks for Signal Processing Pub Date : 1995-08-31 DOI: 10.1109/NNSP.1995.514933
N. Kumar, G. Cauwenberghs, A. Andreou
{"title":"Level crossing time interval circuit for micro-power analog VLSI auditory processing","authors":"N. Kumar, G. Cauwenberghs, A. Andreou","doi":"10.1109/NNSP.1995.514933","DOIUrl":"https://doi.org/10.1109/NNSP.1995.514933","url":null,"abstract":"A low-power circuit for level crossing interval measurements on continuous-time auditory signals, as obtained from the outputs of an analog cochlear filter bank, has been designed and fabricated. Experimental results from a fabricated array of 9 level crossing transducers demonstrate frequency-to-voltage conversion over a range covering the audio band. The power consumption is less than 20 /spl mu/W per cell from a 5 V supply, for the speech frequency range.","PeriodicalId":403144,"journal":{"name":"Proceedings of 1995 IEEE Workshop on Neural Networks for Signal Processing","volume":"18 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1995-08-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"120963732","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
A parallel mapping of backpropagation algorithm for mesh signal processor 网格信号处理器的并行映射反向传播算法
Proceedings of 1995 IEEE Workshop on Neural Networks for Signal Processing Pub Date : 1995-08-31 DOI: 10.1109/NNSP.1995.514931
S. A. Khan, V.K. Madisetti
{"title":"A parallel mapping of backpropagation algorithm for mesh signal processor","authors":"S. A. Khan, V.K. Madisetti","doi":"10.1109/NNSP.1995.514931","DOIUrl":"https://doi.org/10.1109/NNSP.1995.514931","url":null,"abstract":"Presents a technique for mapping the backpropagation learning algorithm on a mesh signal processor. The optimal sub-partitioning of computation and communication, and data replication techniques are the key features of the authors' algorithm. Theoretical analysis and simulation results, using the MIT Lincoln Lab simulator, show that the authors' scheme performs better than the other schemes.","PeriodicalId":403144,"journal":{"name":"Proceedings of 1995 IEEE Workshop on Neural Networks for Signal Processing","volume":"484 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1995-08-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123557300","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
Scaling down: applying large vocabulary hybrid HMM-MLP methods to telephone recognition of digits and natural numbers 缩小:将大词汇量混合HMM-MLP方法应用于数字和自然数的电话识别
Proceedings of 1995 IEEE Workshop on Neural Networks for Signal Processing Pub Date : 1995-08-31 DOI: 10.1109/NNSP.1995.514896
K. Ma, Nelson Morgan
{"title":"Scaling down: applying large vocabulary hybrid HMM-MLP methods to telephone recognition of digits and natural numbers","authors":"K. Ma, Nelson Morgan","doi":"10.1109/NNSP.1995.514896","DOIUrl":"https://doi.org/10.1109/NNSP.1995.514896","url":null,"abstract":"The hybrid hidden Markov model (HMM)/neural network (NN) speech recognition system at the International Computer Science Institute (ICSI) uses a single hidden layer multilayer perceptron (MLP) to compute emission probabilities of HMM states. This phoneme-based recognition approach was developed for large vocabulary size continuous speech recognition. In this paper, however, such a recognition scheme is applied directly to much smaller vocabulary size corpora, such as the Spoken Language Understanding Numbers'93 database and the TI connected digits. The authors report on the development of small baseline systems to facilitate all future research experiments, and also on the use of these systems for experiments in context-dependent hybrid HMM-MLP systems.","PeriodicalId":403144,"journal":{"name":"Proceedings of 1995 IEEE Workshop on Neural Networks for Signal Processing","volume":"20 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1995-08-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123572555","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
Digital neuroimplementations of visual motion-tracking systems 视觉运动跟踪系统的数字神经实现
Proceedings of 1995 IEEE Workshop on Neural Networks for Signal Processing Pub Date : 1995-08-31 DOI: 10.1109/NNSP.1995.514932
A. Colla, L. Trogu, R. Zunino
{"title":"Digital neuroimplementations of visual motion-tracking systems","authors":"A. Colla, L. Trogu, R. Zunino","doi":"10.1109/NNSP.1995.514932","DOIUrl":"https://doi.org/10.1109/NNSP.1995.514932","url":null,"abstract":"The paper describes the implementation of neural systems for visual motion tracking on a digital neurocomputing platform, i.e., the NLX420 Neural Processing Slice. The chip architecture and the problem model considered greatly facilitate the implementation task, which involves the fulfilment of critical real-time constraints. Experimental results confirm the approach validity in terms of both speed and prediction accuracy; training adjustment techniques are also examined.","PeriodicalId":403144,"journal":{"name":"Proceedings of 1995 IEEE Workshop on Neural Networks for Signal Processing","volume":"68 1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1995-08-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132794144","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
Nonlinear echo cancellation using a partial adaptive time delay neural network 基于部分自适应时滞神经网络的非线性回波消除
Proceedings of 1995 IEEE Workshop on Neural Networks for Signal Processing Pub Date : 1995-08-31 DOI: 10.1109/NNSP.1995.514919
A. N. Birkett, R. Goubran
{"title":"Nonlinear echo cancellation using a partial adaptive time delay neural network","authors":"A. N. Birkett, R. Goubran","doi":"10.1109/NNSP.1995.514919","DOIUrl":"https://doi.org/10.1109/NNSP.1995.514919","url":null,"abstract":"System identification of a nonlinear loudspeaker/microphone acoustic system is necessary to achieve high acoustic echo cancellation in the handsfree telephony environments where the loudspeaker often operates at high volumes. In this paper, a partial adaptive process consisting of a small order tapped delay line neural network (TDNN) followed by a delayed normalized least mean squares (NLMS) adaptive filter is used to model a loudspeaker/microphone acoustic system. The TDNN models the first part of the acoustic impulse response (AIR) where most of the energy is contained and the delayed NLMS filter models the remaining echo. Experimental measurements confirm that a short length TDNN is capable of improved identification in an undermodelled system and that by extending this to the partial adaptive TDNN structure, the ERLE performance improves by 5.5 dB at high loudspeaker volumes when compared to a NLMS structure.","PeriodicalId":403144,"journal":{"name":"Proceedings of 1995 IEEE Workshop on Neural Networks for Signal Processing","volume":"86 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1995-08-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131335193","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: 11
Motion estimation and segmentation using a recurrent mixture of experts architecture 运动估计和分割使用循环混合专家架构
Proceedings of 1995 IEEE Workshop on Neural Networks for Signal Processing Pub Date : 1995-08-31 DOI: 10.1109/NNSP.1995.514903
Yair Weiss, E. Adelson
{"title":"Motion estimation and segmentation using a recurrent mixture of experts architecture","authors":"Yair Weiss, E. Adelson","doi":"10.1109/NNSP.1995.514903","DOIUrl":"https://doi.org/10.1109/NNSP.1995.514903","url":null,"abstract":"Estimating motion in scenes containing multiple motions remains a difficult problem for computer vision. Here we describe a novel recurrent network architecture which solves this problem by simultaneously estimating motion and segmenting the scene. The network is comprised of locally connected units which carry out simple calculations in parallel. We present simulation results illustrating the successful motion estimation and rapid convergence of the network on real image sequences.","PeriodicalId":403144,"journal":{"name":"Proceedings of 1995 IEEE Workshop on Neural Networks for Signal Processing","volume":"299 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1995-08-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115931549","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: 16
Velocity measurement of granular flow with a Hopfield network 用Hopfield网络测量颗粒流速度
Proceedings of 1995 IEEE Workshop on Neural Networks for Signal Processing Pub Date : 1995-08-31 DOI: 10.1109/NNSP.1995.514912
J. Lee, J. C. Principe, D. Hanes
{"title":"Velocity measurement of granular flow with a Hopfield network","authors":"J. Lee, J. C. Principe, D. Hanes","doi":"10.1109/NNSP.1995.514912","DOIUrl":"https://doi.org/10.1109/NNSP.1995.514912","url":null,"abstract":"The transport of granular flow is common to many industrial processes. This paper discusses a methodology to measure the velocity of dry granular solids down an inclined chute using high speed digital images. Acrylic particles have been used as granular solids in our experiment. First, particles are located using normalized correlation. A technique for measuring the velocities of individual acrylic particles is developed based on a Hopfield network to solve the particle correspondence problem between successive images. A new, rigidity constraint is applied to the Hopfield energy function, and the results show better performance than the conventional cost function.","PeriodicalId":403144,"journal":{"name":"Proceedings of 1995 IEEE Workshop on Neural Networks for Signal Processing","volume":"6 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1995-08-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114368389","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
Empirical generalization assessment of neural network models 神经网络模型的经验泛化评价
Proceedings of 1995 IEEE Workshop on Neural Networks for Signal Processing Pub Date : 1995-08-31 DOI: 10.1109/NNSP.1995.514876
Jan Larsen, Lars Kai Hansen
{"title":"Empirical generalization assessment of neural network models","authors":"Jan Larsen, Lars Kai Hansen","doi":"10.1109/NNSP.1995.514876","DOIUrl":"https://doi.org/10.1109/NNSP.1995.514876","url":null,"abstract":"This paper addresses the assessment of generalization performance of neural network models by use of empirical techniques. We suggest to use the cross-validation scheme combined with a resampling technique to obtain an estimate of the generalization performance distribution of a specific model. This enables the formulation of a bulk of new generalization performance measures. Numerical results demonstrate the viability of the approach compared to the standard technique of using algebraic estimates like the FPE. Moreover, we consider the problem of comparing the generalization performance of different competing models. Since all models are trained on the same data, a key issue is to take this dependency into account. The optimal split of the data set of size N into a cross-validation set of size N/spl gamma/ and a training set of size N(1-/spl gamma/) is discussed. Asymptotically (large data sees), /spl gamma//sub opt//spl rarr/1 such that a relatively larger amount is left for validation.","PeriodicalId":403144,"journal":{"name":"Proceedings of 1995 IEEE Workshop on Neural Networks for Signal Processing","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1995-08-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128731732","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: 20
Dynamics of associative memory with a self-consistent noise 具有自洽噪声的联想记忆动力学
Proceedings of 1995 IEEE Workshop on Neural Networks for Signal Processing Pub Date : 1995-08-31 DOI: 10.1109/NNSP.1995.514890
I. Opris
{"title":"Dynamics of associative memory with a self-consistent noise","authors":"I. Opris","doi":"10.1109/NNSP.1995.514890","DOIUrl":"https://doi.org/10.1109/NNSP.1995.514890","url":null,"abstract":"The Glauber dynamics of magnetic systems has been extended to the case of neural networks with a general odd response function. The author derives a set of recursion relations for the overlap parameter, noise average and noise variance taken as macrovariables of the process describing the dynamics of associative memory. The retrieval process is studied then for a hyperbolic tangent transfer function by the self-consistent signal to noise ratio method. It takes into account the fatigue effect of the real neuron. The phase diagrams of the retrieval process reveals an enhanced storage capacity for a certain set of parameter values.","PeriodicalId":403144,"journal":{"name":"Proceedings of 1995 IEEE Workshop on Neural Networks for Signal Processing","volume":"23 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1995-08-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125107922","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
Discriminative Subspace Method for Minimum Error Pattern Recognition 最小误差模式识别的判别子空间方法
Proceedings of 1995 IEEE Workshop on Neural Networks for Signal Processing Pub Date : 1995-08-31 DOI: 10.1109/NNSP.1995.514881
H. Watanabe, S. Katagiri
{"title":"Discriminative Subspace Method for Minimum Error Pattern Recognition","authors":"H. Watanabe, S. Katagiri","doi":"10.1109/NNSP.1995.514881","DOIUrl":"https://doi.org/10.1109/NNSP.1995.514881","url":null,"abstract":"Subspace Method (SM) is one of fundamental frameworks for pattern recognition. In particular, its discriminative learning version, called Learning Subspace Method (LSM), has been shown quite useful in various applications. However, this important design method leaves much room for further analysis due to the lack of a link between LSM and the ultimate goal of pattern recognition, i.e. the minimum error situation. In this light, we investigate in this paper SM from the viewpoint of the Minimum Classification Error/Generalized Probabilistic Descent method (MCE/GPD). Applying MCE/GPD to SM, we formalize a new discriminative subspace method, called the Minimum Error Learning Subspace method (MELS), which enables one to directly pursue the minimum error recognition. This paper also provides a rigorous analysis of the MELS’s learning mechanism as well as a comparison between the conventional LSM and MELS.","PeriodicalId":403144,"journal":{"name":"Proceedings of 1995 IEEE Workshop on Neural Networks for Signal Processing","volume":"15 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1995-08-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125642521","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: 29
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