发布求助
文献互助 智能选刊 最新文献

Proceedings of the 2002 International Joint Conference on Neural Networks. IJCNN'02 (Cat. No.02CH37290)最新文献

筛选
英文 中文
Who is afraid of the big bad ANN? 谁害怕大坏的人工神经网络?
Proceedings of the 2002 International Joint Conference on Neural Networks. IJCNN'02 (Cat. No.02CH37290) Pub Date : 2002-08-07 DOI: 10.1109/IJCNN.2002.1007444
Z. Boger
{"title":"Who is afraid of the big bad ANN?","authors":"Z. Boger","doi":"10.1109/IJCNN.2002.1007444","DOIUrl":"https://doi.org/10.1109/IJCNN.2002.1007444","url":null,"abstract":"The author's ten-year experience with training large-scale ANN models with the PCA-CG algorithm that generates a non-random initial connection weight set is presented. The suggested small number of hidden neurons and automatic identification and removal of the less relevant inputs increases the robustness of these models. Examples of ANN modeling of \"artificial nose\" sensor array, TV program rating and e-mail letter importance classification demonstrate the algorithm efficiency.","PeriodicalId":382771,"journal":{"name":"Proceedings of the 2002 International Joint Conference on Neural Networks. IJCNN'02 (Cat. No.02CH37290)","volume":"121 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2002-08-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134253963","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 hierarchical approach to ART-like clustering algorithm 一种分层的类art聚类算法
Proceedings of the 2002 International Joint Conference on Neural Networks. IJCNN'02 (Cat. No.02CH37290) Pub Date : 2002-08-07 DOI: 10.1109/IJCNN.2002.1005574
M. Su, Yi-Chun Liu
{"title":"A hierarchical approach to ART-like clustering algorithm","authors":"M. Su, Yi-Chun Liu","doi":"10.1109/IJCNN.2002.1005574","DOIUrl":"https://doi.org/10.1109/IJCNN.2002.1005574","url":null,"abstract":"We propose a hierarchical approach to ART-like clustering algorithm which is able to deal with data consisting of arbitrarily geometrical-shaped clusters. A combined hierarchical and ART-like clustering is suggested as a natural feasible solution to the two problems of determining the number of clusters and clustering data. A 2D artificial data set is tested to demonstrate the performance of the proposed algorithm.","PeriodicalId":382771,"journal":{"name":"Proceedings of the 2002 International Joint Conference on Neural Networks. IJCNN'02 (Cat. No.02CH37290)","volume":"26 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2002-08-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134553921","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: 7
An auditory system for efficient coding of natural sounds 对自然声音进行有效编码的听觉系统
Proceedings of the 2002 International Joint Conference on Neural Networks. IJCNN'02 (Cat. No.02CH37290) Pub Date : 2002-08-07 DOI: 10.1109/IJCNN.2002.1005436
S. Maeda, S. Ishii
{"title":"An auditory system for efficient coding of natural sounds","authors":"S. Maeda, S. Ishii","doi":"10.1109/IJCNN.2002.1005436","DOIUrl":"https://doi.org/10.1109/IJCNN.2002.1005436","url":null,"abstract":"Presents a model of the auditory pathway. The model consists of two parts; one is nonlinear transformation and the other is sparse coding to reduce the dependency involved in the transformed signal. The later part theoretically corresponds to noisy independent component analysis. The two parts individually learn so as to maximize the entropy. The model can well reproduce a couple of biological phenomena observed in the auditory system. They are virtual pitch and masking effect. These results imply that the nonlinear transformation by single neurons and the transformation realized by neural populations play essential roles to obtain efficient information processing, i.e., coding, in the primary auditory system. This is consistent with results in the primary visual system, which have introduced the notion of maximum entropy criterion and sparse coding.","PeriodicalId":382771,"journal":{"name":"Proceedings of the 2002 International Joint Conference on Neural Networks. IJCNN'02 (Cat. No.02CH37290)","volume":"38 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2002-08-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133866077","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
On the dynamic behavior of cellular neural networks 细胞神经网络的动态行为
Proceedings of the 2002 International Joint Conference on Neural Networks. IJCNN'02 (Cat. No.02CH37290) Pub Date : 2002-08-07 DOI: 10.1109/IJCNN.2002.1007815
M. Gilli, F. Corinto, M. Biey, P. Civalleri
{"title":"On the dynamic behavior of cellular neural networks","authors":"M. Gilli, F. Corinto, M. Biey, P. Civalleri","doi":"10.1109/IJCNN.2002.1007815","DOIUrl":"https://doi.org/10.1109/IJCNN.2002.1007815","url":null,"abstract":"Cellular neural networks (CNNs) are analog dynamic processors that have found several applications for the solution of complex computational problems. The mathematical model of a CNN consists in a large set of coupled nonlinear differential equations that have been mainly studied through numerical simulations; the knowledge of the dynamic behavior is essential for developing rigorous design methods and for establishing new applications. CNNs can be divided in two classes: stable CNNs, with the property that each trajectory (with the exception of a set of measure zero) converges towards an equilibrium point; unstable CNNs with either a periodic or a non/periodic (possibly complex) behavior. The paper is devoted to the comparison of the dynamic behavior of two CNN models: the original Chua-Yang model and the full range model, that was exploited for VLSI implementations.","PeriodicalId":382771,"journal":{"name":"Proceedings of the 2002 International Joint Conference on Neural Networks. IJCNN'02 (Cat. No.02CH37290)","volume":"267 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2002-08-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133888933","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
An ensemble learning approach to nonlinear dynamic blind source separation using state-space models 基于状态空间模型的非线性动态盲源分离集成学习方法
Proceedings of the 2002 International Joint Conference on Neural Networks. IJCNN'02 (Cat. No.02CH37290) Pub Date : 2002-08-07 DOI: 10.1109/IJCNN.2002.1005516
H. Valpola, A. Honkela, J. Karhunen
{"title":"An ensemble learning approach to nonlinear dynamic blind source separation using state-space models","authors":"H. Valpola, A. Honkela, J. Karhunen","doi":"10.1109/IJCNN.2002.1005516","DOIUrl":"https://doi.org/10.1109/IJCNN.2002.1005516","url":null,"abstract":"We propose a new method for learning a nonlinear dynamical state-space model in unsupervised manner. The proposed method can be viewed as a nonlinear dynamic generalization of standard linear blind source separation (BSS) or independent component analysis (ICA). Using ensemble learning, the method finds a nonlinear dynamical process which can explain the observations. The nonlinearities are modeled with multilayer perceptron networks. In ensemble learning, a simpler approximative distribution is fitted to the true posterior distribution by minimizing their Kullback-Leibler divergence. This also regularizes the studied highly ill-posed problem. In an experiment with a difficult chaotic data set, the proposed method found a much better model for the underlying dynamical process and source signals used for generating the data than the compared methods.","PeriodicalId":382771,"journal":{"name":"Proceedings of the 2002 International Joint Conference on Neural Networks. IJCNN'02 (Cat. No.02CH37290)","volume":"5 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2002-08-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133991033","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
A novel learning model for intelligent agents 一种新的智能体学习模型
Proceedings of the 2002 International Joint Conference on Neural Networks. IJCNN'02 (Cat. No.02CH37290) Pub Date : 2002-08-07 DOI: 10.1109/IJCNN.2002.1007602
D. Varmette, J. Baghdadchi
{"title":"A novel learning model for intelligent agents","authors":"D. Varmette, J. Baghdadchi","doi":"10.1109/IJCNN.2002.1007602","DOIUrl":"https://doi.org/10.1109/IJCNN.2002.1007602","url":null,"abstract":"The objective of this study is to synthesize a learning model capable of successful and effective operation in hard-to-model environments. Here, we are presenting a structurally simple and functionally flexible model. The model follows the learning patterns experienced by humans. The novelty of the adaptive model lies on the knowledge base and the learning strategy. The knowledge base is allowed to grow for as long as the agent lives. Learning is brought about by the interaction between two qualitatively different activities, leaving long-term and short-term marks on the behavior of the agent. The agent reaches conclusions using approximate reasoning. The focus of the model, the agent, starts life with a blank knowledge base, and learns as it lives. Classifiers are used to represent individual experiences. We demonstrate functionality of the model through a case study.","PeriodicalId":382771,"journal":{"name":"Proceedings of the 2002 International Joint Conference on Neural Networks. IJCNN'02 (Cat. No.02CH37290)","volume":"33 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2002-08-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134298137","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
Using neural network models for efficient GaAs MESFET time domain nonlinear circuit analysis 利用神经网络模型对高效GaAs MESFET进行时域非线性电路分析
Proceedings of the 2002 International Joint Conference on Neural Networks. IJCNN'02 (Cat. No.02CH37290) Pub Date : 2002-08-07 DOI: 10.1109/IJCNN.2002.1007497
P. H. da Fonseca Silva, M. D. de Melo, A. Neto
{"title":"Using neural network models for efficient GaAs MESFET time domain nonlinear circuit analysis","authors":"P. H. da Fonseca Silva, M. D. de Melo, A. Neto","doi":"10.1109/IJCNN.2002.1007497","DOIUrl":"https://doi.org/10.1109/IJCNN.2002.1007497","url":null,"abstract":"This paper describes the applications of multilayer perceptrons for GaAs device and integrated circuit modeling, that were proposed to improve circuit simulation programs like SPICE. The obtained results by the MESFET logic gate circuit simulations prove the validation of neural models applicability for the time domain nonlinear circuit transient and sensitivity analyses.","PeriodicalId":382771,"journal":{"name":"Proceedings of the 2002 International Joint Conference on Neural Networks. IJCNN'02 (Cat. No.02CH37290)","volume":"21 4","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2002-08-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131726127","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
Implicit learning in autoencoder novelty assessment 自编码器新颖性评估中的内隐学习
Proceedings of the 2002 International Joint Conference on Neural Networks. IJCNN'02 (Cat. No.02CH37290) Pub Date : 2002-08-07 DOI: 10.1109/IJCNN.2002.1007605
B.B. Thompson, Robert J. Marks, Jai J Choi, Mohamed A. El-Sharkawi, Ming-Yuh Huang, Carl Bunje
{"title":"Implicit learning in autoencoder novelty assessment","authors":"B.B. Thompson, Robert J. Marks, Jai J Choi, Mohamed A. El-Sharkawi, Ming-Yuh Huang, Carl Bunje","doi":"10.1109/IJCNN.2002.1007605","DOIUrl":"https://doi.org/10.1109/IJCNN.2002.1007605","url":null,"abstract":"When the situation arises that only \"normal\" behavior is known about a system, it is desirable to develop a system based solely on that behavior which enables the user to determine when that system behavior falls outside of that range of normality. A new method is proposed for detecting such novel behavior through the use of autoassociative neural network encoders, which can be shown to implicitly learn the nature of the underlying \"normal\" system behavior.","PeriodicalId":382771,"journal":{"name":"Proceedings of the 2002 International Joint Conference on Neural Networks. IJCNN'02 (Cat. No.02CH37290)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2002-08-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"117334656","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: 78
Audio/video compression applications using wavelets 使用小波的音频/视频压缩应用
Proceedings of the 2002 International Joint Conference on Neural Networks. IJCNN'02 (Cat. No.02CH37290) Pub Date : 2002-08-07 DOI: 10.1109/IJCNN.2002.1007485
Yuxiao Cheng, Gen-Dow Huang
{"title":"Audio/video compression applications using wavelets","authors":"Yuxiao Cheng, Gen-Dow Huang","doi":"10.1109/IJCNN.2002.1007485","DOIUrl":"https://doi.org/10.1109/IJCNN.2002.1007485","url":null,"abstract":"It is well known that the advantages of wavelet transform are to provide characteristic of multiple resolution and global decomposition that are the significant features for the audio/video compression applications. In this paper, an effective wavelet-based audio/video compression algorithm is presented to provide highly efficient signal compression mechanism with acceptable human visual/hearing perception. Experimental simulations show that the proposed audio/video model can meet the current industrial communication requirements in terms of the processing time and the compression performance. Development of wavelet-based audio/video compression model also includes the consideration of hardware implementation. With this high-performance audio and video codec, it can be employed to develop compact, low power, high-speed, portable, cost-effective, and low-weight video/audio compression multimedia application.","PeriodicalId":382771,"journal":{"name":"Proceedings of the 2002 International Joint Conference on Neural Networks. IJCNN'02 (Cat. No.02CH37290)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2002-08-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131166072","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
Adaptive channel equalization using EKF-CRTRL neural networks 利用 EKF-CRTRL 神经网络实现自适应信道均衡
Proceedings of the 2002 International Joint Conference on Neural Networks. IJCNN'02 (Cat. No.02CH37290) Pub Date : 2002-08-07 DOI: 10.1109/IJCNN.2002.1007664
P. Henrique, G. Coelho
{"title":"Adaptive channel equalization using EKF-CRTRL neural networks","authors":"P. Henrique, G. Coelho","doi":"10.1109/IJCNN.2002.1007664","DOIUrl":"https://doi.org/10.1109/IJCNN.2002.1007664","url":null,"abstract":"The purpose of this paper is to apply the complex real time recurrent learning-fully recurrent neural network extended Kalman filter (CRTRL-EKF), trained in an adaptive equalization for cellular communications channels. Numerical results are presented to illustrate the method using the wide sense stationary-uncorrelated scattering channel model.","PeriodicalId":382771,"journal":{"name":"Proceedings of the 2002 International Joint Conference on Neural Networks. IJCNN'02 (Cat. No.02CH37290)","volume":"57 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2002-08-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131039353","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
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