Proceedings of the International Joint Conference on Neural Networks, 2003.最新文献_第2页

Radial basis network approach for nonlinear filtering in discrete time 离散时间非线性滤波的径向基网络方法

Proceedings of the International Joint Conference on Neural Networks, 2003. Pub Date : 2003-07-20 DOI: 10.1109/IJCNN.2003.1223945

V. Rossi, J. Vila

引用次数: 0

Time-series novelty detection using one-class support vector machines 一类支持向量机的时间序列新颖性检测

Proceedings of the International Joint Conference on Neural Networks, 2003. Pub Date : 2003-07-20 DOI: 10.1109/IJCNN.2003.1223670

Junshui Ma, S. Perkins

引用次数: 343

Support vector visualization and clustering using self-organizing map and vector one-class classification 支持向量可视化和聚类使用自组织地图和向量一类分类

Proceedings of the International Joint Conference on Neural Networks, 2003. Pub Date : 2003-07-20 DOI: 10.1109/IJCNN.2003.1223485

Sitao Wu, T. Chow

引用次数: 6

Noise supplement learning algorithm for associative memories using multilayer perceptrons and sparsely interconnected neural networks 基于多层感知器和稀疏互联神经网络的联想记忆噪声补充学习算法

Proceedings of the International Joint Conference on Neural Networks, 2003. Pub Date : 2003-07-20 DOI: 10.1109/IJCNN.2003.1223964

Y. Magori, T. Kamio, H. Fujisaka, M. Morisue

引用次数: 1

Clustering in coupled maps on small-world networks 小世界网络上耦合映射的聚类

Proceedings of the International Joint Conference on Neural Networks, 2003. Pub Date : 2003-07-20 DOI: 10.1109/IJCNN.2003.1223368

R. de Oliveira, L. Monteiro

引用次数: 3

Early striate activity related to attention in a choice reaction task 早期纹状体活动与选择反应任务中的注意力有关

Proceedings of the International Joint Conference on Neural Networks, 2003. Pub Date : 2003-07-20 DOI: 10.1109/IJCNN.2003.1223358

V. Poghosyan, Tadahiko Shibata, Peter B. C. Fenwick, Lichan Liu, A. A. Ioannides

{"title":"Early striate activity related to attention in a choice reaction task","authors":"V. Poghosyan, Tadahiko Shibata, Peter B. C. Fenwick, Lichan Liu, A. A. Ioannides","doi":"10.1109/IJCNN.2003.1223358","DOIUrl":"https://doi.org/10.1109/IJCNN.2003.1223358","url":null,"abstract":"Attentional effects in the striate and extrastriate cortex have been the subject of intense research interest in many recent studies using single unit recordings in animals and neuroimaging methods in humans. The consensus emerging from these studies places attentional effects first in extrastriate areas. Attentional influence in this view is reaching V1 rather late, some 150 ms after stimulus onset, well after the main N1/P1 complex which peaks about 50 ms earlier. We show here that an earlier wave of attentional effects is present in V1 beginning soon after 50 ms and reaching a peak between 90 and 100 ms after stimulus onset. This effect is identified in a comparison of passive viewing of stimuli and an active GO/NOGO task using the same stimuli. The effect was best seen in the tomographic analysis of single trial magnetoencephalographic (MEG) data, designed to cope with simultaneous activations throughout the brain at each timeslice. This early attentional modulation might still be interpreted as a modulation of the striate cortex from extrastriate areas because attention related changes are present in the prestimulus period in both dorsal and ventral extrastriate areas.","PeriodicalId":310128,"journal":{"name":"Proceedings of the International Joint Conference on Neural Networks, 2003.","volume":"21 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2003-07-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122015364","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

Modeling CMOS gate characteristics using independent component analysis 利用独立分量分析建模CMOS栅极特性

Proceedings of the International Joint Conference on Neural Networks, 2003. Pub Date : 2003-07-20 DOI: 10.1109/IJCNN.2003.1223486

T. Shannon, D. Abercrombie, J. Mcnames

引用次数: 1

Electrotonic effects on spike response model dynamics 电紧张效应对脉冲响应模型动力学的影响

Proceedings of the International Joint Conference on Neural Networks, 2003. Pub Date : 2003-07-20 DOI: 10.1109/IJCNN.2003.1224020

G. Ascoli

{"title":"Electrotonic effects on spike response model dynamics","authors":"G. Ascoli","doi":"10.1109/IJCNN.2003.1224020","DOIUrl":"https://doi.org/10.1109/IJCNN.2003.1224020","url":null,"abstract":"According to dendritic cable theory, proximal synapses give rise to inputs with short delay, high amplitude, and short duration. In contrast, inputs from distal synapses have long delays, low amplitude, and long duration. Large scale neural networks are seldom built with realistically layered synaptic architectures and corresponding electrotonic parameters. A complete representation of electrotonic dynamics implies the computationally expensive solution of cable differential equations. Here, we use a simpler model to investigate the spike response dynamics of networks with different electrotonic structures. The networks consist of a layer of neurons receiving a sparse feedforward projection from a set of inputs, as well as sparse recurrent connections from within the layer. Firing patterns are set in the set of inputs, and recorded from the neuron (output) layer. The feedforward and recurrent synapses are independently set as proximal or distal, representing dendritic connections near or far from the soma, respectively. Analyses of firing dynamics indicate that recurrent distal synapses tend to concentrate network activity in fewer neurons, while proximal recurrent synapses result in a more homogeneous activity distribution. In addition, when the feedforward input is regular (spiking or bursting) and asynchronous, the output is regular if recurrent synapses are more distal than feedforward ones, and irregular in the opposite configuration. Finally, the amplitude of network fluctuations in response to asynchronous input is lower if feedforward and recurrent synapses are electrotonically distant from one another (in either configuration). In conclusion, electrotonic effects reflecting different dendritic positions of synaptic inputs significantly influence network dynamics.","PeriodicalId":310128,"journal":{"name":"Proceedings of the International Joint Conference on Neural Networks, 2003.","volume":"45 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2003-07-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128775658","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

Evolutionary computation for dynamic parameter optimisation of evolving connectionist systems for on-line prediction of time series with changing dynamics 演化连接系统动态参数优化的演化计算，用于动态变化时间序列的在线预测

Proceedings of the International Joint Conference on Neural Networks, 2003. Pub Date : 2003-07-20 DOI: 10.1109/IJCNN.2003.1223386

N. Kasabov, Q. Song, I. Nishikanawa

引用次数: 11

Fault tolerance of feedforward artificial neural networks- a framework of study 前馈人工神经网络容错研究框架

Proceedings of the International Joint Conference on Neural Networks, 2003. Pub Date : 2003-07-20 DOI: 10.1109/IJCNN.2003.1223395

P. Chandra, Y. Singh

引用次数: 40