Pub Date : 2006-10-30DOI: 10.1109/IJCNN.2006.246919
Sergio Silva, A. Ruano
One of the basic aspects of some neural networks is their attempt to approximate as much as possible their biological counterparts. The goal is to achieve a simple and robust network, easy to comprehend and capable of simulating the human brain at a computational level. This paper presents improvements to the Spikepro algorithm, by introducing a new encoding scheme, and illustrate the application of the Levenberg Marquardt algorithm to this third generation of neural network
{"title":"Application of Levenberg-Marquardt method to the training of spiking neural networks","authors":"Sergio Silva, A. Ruano","doi":"10.1109/IJCNN.2006.246919","DOIUrl":"https://doi.org/10.1109/IJCNN.2006.246919","url":null,"abstract":"One of the basic aspects of some neural networks is their attempt to approximate as much as possible their biological counterparts. The goal is to achieve a simple and robust network, easy to comprehend and capable of simulating the human brain at a computational level. This paper presents improvements to the Spikepro algorithm, by introducing a new encoding scheme, and illustrate the application of the Levenberg Marquardt algorithm to this third generation of neural network","PeriodicalId":145719,"journal":{"name":"2005 International Conference on Neural Networks and Brain","volume":"54 67 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2006-10-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131168573","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}
Pub Date : 2006-10-23DOI: 10.1109/WCICA.2006.1712891
Quan Liu, Xuemei Jiang
A meaningful digital image watermarking algorithm based on RBF (radial basis function neural network) neural network is proposed in this paper. RBF neural network is used to simulate human visual speciality to determine the watermark embedding intensity endured by DCT coefficients and the watermarking is a meaningful two value image. It is pre-treated by Arnold scrambling algorithm, and then is embedded into DCT coefficients. So this algorithm has good stability. The experiments of results show that the algorithm has good robustness against all kinds of attacks
{"title":"Design and Realization of a Meaningful Digital Watermarking Algorithm Based on RBF Neural Network*","authors":"Quan Liu, Xuemei Jiang","doi":"10.1109/WCICA.2006.1712891","DOIUrl":"https://doi.org/10.1109/WCICA.2006.1712891","url":null,"abstract":"A meaningful digital image watermarking algorithm based on RBF (radial basis function neural network) neural network is proposed in this paper. RBF neural network is used to simulate human visual speciality to determine the watermark embedding intensity endured by DCT coefficients and the watermarking is a meaningful two value image. It is pre-treated by Arnold scrambling algorithm, and then is embedded into DCT coefficients. So this algorithm has good stability. The experiments of results show that the algorithm has good robustness against all kinds of attacks","PeriodicalId":145719,"journal":{"name":"2005 International Conference on Neural Networks and Brain","volume":"35 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2006-10-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114828765","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}
We propose a multiscale feature extraction method of finger-vein patterns based on wavelet and local interconnection structure neural networks. The finger-vein image is performed the multiscale self-adaptive enhancement transform. A neural network with local interconnection structure is designed to extract the features of the finger-vein pattern. This method has three features: Firstly, by applying the multiscale self-adaptive enhancement transform to the finger-vein image, the finger-vein pattern is emphasized and noises are refrained. Secondly, we use different receptive fields to deal with different size finger-rein patterns. This and the multiscale property of the wavelet analysis lead to accurate extraction of different size finger-rein modes. Thirdly, our method is very fast by using the integral image method. The experimental results show the proposed method is superior to other methods and solve the problem of extracting features from the unclear images efficiently. The EER of the proposed method is 0.130% in personal identification
{"title":"Multiscale Feature Extraction of Finger-Vein Patterns Based on Wavelet and Local Interconnection Structure Neural Network","authors":"Zhongbo Zhang, Siliang Ma, Xiao Han","doi":"10.1109/ICPR.2006.848","DOIUrl":"https://doi.org/10.1109/ICPR.2006.848","url":null,"abstract":"We propose a multiscale feature extraction method of finger-vein patterns based on wavelet and local interconnection structure neural networks. The finger-vein image is performed the multiscale self-adaptive enhancement transform. A neural network with local interconnection structure is designed to extract the features of the finger-vein pattern. This method has three features: Firstly, by applying the multiscale self-adaptive enhancement transform to the finger-vein image, the finger-vein pattern is emphasized and noises are refrained. Secondly, we use different receptive fields to deal with different size finger-rein patterns. This and the multiscale property of the wavelet analysis lead to accurate extraction of different size finger-rein modes. Thirdly, our method is very fast by using the integral image method. The experimental results show the proposed method is superior to other methods and solve the problem of extracting features from the unclear images efficiently. The EER of the proposed method is 0.130% in personal identification","PeriodicalId":145719,"journal":{"name":"2005 International Conference on Neural Networks and Brain","volume":"27 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2006-08-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125086227","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}
Pub Date : 2006-04-10DOI: 10.1109/ICNNB.2005.1614697
D.M. Kawato
In ATR Computational Neuroscience Laboratories neurophysiological and robotics studies explored several key concepts such as cerebellar internal models, multiple internal models, MOSAIC, imitation learning, biologically motivated robot biped locomotion, modular and hierarchical reinforcement learning models. Recent efforts in ATR CNS labs including computational-model based imaging, hierarchical variational Bayesian method in fMRI-MEG combination, and robotics experiments could be the bases of the new methodology in neuroscience
{"title":"Connecting Brains and Robots by Computational Theories","authors":"D.M. Kawato","doi":"10.1109/ICNNB.2005.1614697","DOIUrl":"https://doi.org/10.1109/ICNNB.2005.1614697","url":null,"abstract":"In ATR Computational Neuroscience Laboratories neurophysiological and robotics studies explored several key concepts such as cerebellar internal models, multiple internal models, MOSAIC, imitation learning, biologically motivated robot biped locomotion, modular and hierarchical reinforcement learning models. Recent efforts in ATR CNS labs including computational-model based imaging, hierarchical variational Bayesian method in fMRI-MEG combination, and robotics experiments could be the bases of the new methodology in neuroscience","PeriodicalId":145719,"journal":{"name":"2005 International Conference on Neural Networks and Brain","volume":"91 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2006-04-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115087330","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}
Pub Date : 2006-04-10DOI: 10.1109/ICNNB.2005.1614538
A. Guo
Drosophila flies can be trained in the flight simulator to operantly avoid heat by choosing certain flight orientations relative to landmarks. Flies primarily store pattern orientations associated with the absence of heat. They readily escape from heat-associated orientations under the direct influence of the reinforcer but not in the subsequent memory tests. This paper shows that Drosophila flies could be used as a new model organism for the neurobiology of cognition-like behavior
{"title":"Natural Computation: Decision-Making Facing Conflicting Visual Cues And Crossmodal Interaction Between Olfactory And Visual Learning In Drosophila","authors":"A. Guo","doi":"10.1109/ICNNB.2005.1614538","DOIUrl":"https://doi.org/10.1109/ICNNB.2005.1614538","url":null,"abstract":"Drosophila flies can be trained in the flight simulator to operantly avoid heat by choosing certain flight orientations relative to landmarks. Flies primarily store pattern orientations associated with the absence of heat. They readily escape from heat-associated orientations under the direct influence of the reinforcer but not in the subsequent memory tests. This paper shows that Drosophila flies could be used as a new model organism for the neurobiology of cognition-like behavior","PeriodicalId":145719,"journal":{"name":"2005 International Conference on Neural Networks and Brain","volume":"2 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2006-04-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127833326","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}
Pub Date : 2006-04-10DOI: 10.1109/ICNNB.2005.1614534
E. Oja
In many fields of science, engineering, medicine and economics, large or huge data sets are routinely collected. Processing and transforming such data to intelligible form for the human user is becoming one of the most urgent problems in near future. Neural networks and related statistical machine learning methods have turned out to be promising solutions. In many cases, the data matrix has both a spatial and a temporal dimension. Removing correlations and thus reducing the dimensionality is typically the first step in the processing. After this, higher-order statistical methods such as independent component analysis can often reveal the structure of the data by finding hidden factors. This can sometimes be enhanced by semi-blind techniques such as temporal filtering in order to use prior knowledge. Examples to be covered in the talk are biomedical fMRI data and long-term climate data, both having dimensionalities in the tens of thousands. Recent results are shown on brain activations to stimuli and on climate patterns.
{"title":"Finding Hidden Factors in Large Spatiotemporal Data Sets","authors":"E. Oja","doi":"10.1109/ICNNB.2005.1614534","DOIUrl":"https://doi.org/10.1109/ICNNB.2005.1614534","url":null,"abstract":"In many fields of science, engineering, medicine and economics, large or huge data sets are routinely collected. Processing and transforming such data to intelligible form for the human user is becoming one of the most urgent problems in near future. Neural networks and related statistical machine learning methods have turned out to be promising solutions. In many cases, the data matrix has both a spatial and a temporal dimension. Removing correlations and thus reducing the dimensionality is typically the first step in the processing. After this, higher-order statistical methods such as independent component analysis can often reveal the structure of the data by finding hidden factors. This can sometimes be enhanced by semi-blind techniques such as temporal filtering in order to use prior knowledge. Examples to be covered in the talk are biomedical fMRI data and long-term climate data, both having dimensionalities in the tens of thousands. Recent results are shown on brain activations to stimuli and on climate patterns.","PeriodicalId":145719,"journal":{"name":"2005 International Conference on Neural Networks and Brain","volume":"2 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2006-04-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123636593","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}
Pub Date : 2005-11-07DOI: 10.1109/ICMLC.2005.1527455
Wen Shuhua, Zhang Xueliang, Liu Hainan, Liu Shuyang, Wang Jiaying
A modified particle swarm optimization (MPSO) algorithm is presented based on the variance of the population's fitness. During computing, the inertia weight of MPSO is determined adaptively and randomly according to the variance of the populations fitness. And the ability of , particle swarm optimization algorithm (PSO) to break away from the local optimum is greatly improved. The simulating results show that this algorithm not only has great advantage of convergence property over standard simple PSO, but also can avoid the premature convergence problem effectively
{"title":"A Modified Particle Swarm Optimization Algorithm","authors":"Wen Shuhua, Zhang Xueliang, Liu Hainan, Liu Shuyang, Wang Jiaying","doi":"10.1109/ICMLC.2005.1527455","DOIUrl":"https://doi.org/10.1109/ICMLC.2005.1527455","url":null,"abstract":"A modified particle swarm optimization (MPSO) algorithm is presented based on the variance of the population's fitness. During computing, the inertia weight of MPSO is determined adaptively and randomly according to the variance of the populations fitness. And the ability of , particle swarm optimization algorithm (PSO) to break away from the local optimum is greatly improved. The simulating results show that this algorithm not only has great advantage of convergence property over standard simple PSO, but also can avoid the premature convergence problem effectively","PeriodicalId":145719,"journal":{"name":"2005 International Conference on Neural Networks and Brain","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2005-11-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132271407","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}
Pub Date : 2005-11-01DOI: 10.1109/TENCON.2005.301294
Junping Du, Wensheng Guo
In this paper, we use machine learning schemes IR, FOIL, InductH and C5.0 to generate decision trees and rules from the examples in the medical dataset. The aim of our study is to infer the patterns that can help doctors to identify, recognize and predict the effect of the risk factors on the long term subjective cure rates of patients who undergo colposuspension. High test classification was sometimes achieved. Our best results came when one learning method suggested the preprocessing steps to be used for another method
{"title":"Data Mining on Patient Data","authors":"Junping Du, Wensheng Guo","doi":"10.1109/TENCON.2005.301294","DOIUrl":"https://doi.org/10.1109/TENCON.2005.301294","url":null,"abstract":"In this paper, we use machine learning schemes IR, FOIL, InductH and C5.0 to generate decision trees and rules from the examples in the medical dataset. The aim of our study is to infer the patterns that can help doctors to identify, recognize and predict the effect of the risk factors on the long term subjective cure rates of patients who undergo colposuspension. High test classification was sometimes achieved. Our best results came when one learning method suggested the preprocessing steps to be used for another method","PeriodicalId":145719,"journal":{"name":"2005 International Conference on Neural Networks and Brain","volume":"44 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2005-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131650980","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}
Pub Date : 2005-10-13DOI: 10.1109/ICNNB.2005.1614838
Lihong Zhao, Yulu Cai, Jinghong Li, Xinhe Xu
Face recognition is a rapidly growing research area due to the increasing demands for the security in commercial and jurally enforcement applications. High information redundancy and correlation in face images result in the inefficiency when such images are used directly for recognition. In this paper, discrete cosine transforms is used to reduce image information redundancy, because only a subset of the transform coefficients are necessary to preserve the most important facial features such as hair outline, eyes and mouth. The experimental results on the ORL face database utilizing the SVM algorithm show that the satisfying recognition performance can be obtained. The correct recognition rate is 96.5%
{"title":"Face Recognition Based on Discrete Cosine Transform and Support Vector Machine","authors":"Lihong Zhao, Yulu Cai, Jinghong Li, Xinhe Xu","doi":"10.1109/ICNNB.2005.1614838","DOIUrl":"https://doi.org/10.1109/ICNNB.2005.1614838","url":null,"abstract":"Face recognition is a rapidly growing research area due to the increasing demands for the security in commercial and jurally enforcement applications. High information redundancy and correlation in face images result in the inefficiency when such images are used directly for recognition. In this paper, discrete cosine transforms is used to reduce image information redundancy, because only a subset of the transform coefficients are necessary to preserve the most important facial features such as hair outline, eyes and mouth. The experimental results on the ORL face database utilizing the SVM algorithm show that the satisfying recognition performance can be obtained. The correct recognition rate is 96.5%","PeriodicalId":145719,"journal":{"name":"2005 International Conference on Neural Networks and Brain","volume":"59 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2005-10-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116701683","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}
Pub Date : 2005-10-13DOI: 10.1109/ICNNB.2005.1614754
He Jin-can, Xu Li-zhong, Yao Hong-xi, Shen Ping
This paper introduces an information fusion methodology, which is based on fuzzy neural network (FNN) and D-S evidence theory, to assess the mine ventilation system safety. This method imports fuzzy rule information, expert language information, etc. to fusion system by using fuzzy neural network, and uses the output of each neural network as the base probability assignment function (BPAF) of D-S evidence theory, and fuses this with the BPAF according to the combination rule of D-S evidence theory, which gives the assessment of the ventilation system. This method improves the systemic anti-jamming ability, and tones up the systemic fault tolerance ability. According to the standard of "Mining Safety Rules, 2005", we get the estimation factorial weight by the statistic data and expert experience and the training stylebook, looking the monitoring data as the validating stylebook. The results of simulation shows that the method can be used to the assessment of ventilation system, and compares it with the other method based on neural network and D-S evidence theory, the precision is higher
{"title":"Mine Ventilation Safety Assessment Based on FNN and D-S Evidence Theory","authors":"He Jin-can, Xu Li-zhong, Yao Hong-xi, Shen Ping","doi":"10.1109/ICNNB.2005.1614754","DOIUrl":"https://doi.org/10.1109/ICNNB.2005.1614754","url":null,"abstract":"This paper introduces an information fusion methodology, which is based on fuzzy neural network (FNN) and D-S evidence theory, to assess the mine ventilation system safety. This method imports fuzzy rule information, expert language information, etc. to fusion system by using fuzzy neural network, and uses the output of each neural network as the base probability assignment function (BPAF) of D-S evidence theory, and fuses this with the BPAF according to the combination rule of D-S evidence theory, which gives the assessment of the ventilation system. This method improves the systemic anti-jamming ability, and tones up the systemic fault tolerance ability. According to the standard of \"Mining Safety Rules, 2005\", we get the estimation factorial weight by the statistic data and expert experience and the training stylebook, looking the monitoring data as the validating stylebook. The results of simulation shows that the method can be used to the assessment of ventilation system, and compares it with the other method based on neural network and D-S evidence theory, the precision is higher","PeriodicalId":145719,"journal":{"name":"2005 International Conference on Neural Networks and Brain","volume":"22 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2005-10-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116951096","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}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：