Proceedings of the International Joint Conference on Neural Networks, 2003.最新文献_第7页

Neural networks applied to classification of data based on Mahalanobis metrics 神经网络应用于基于马氏度量的数据分类

Proceedings of the International Joint Conference on Neural Networks, 2003. Pub Date : 2003-07-20 DOI: 10.1109/IJCNN.2003.1224062

A. De Medeiros Martins, A. Neto, J.D. de Melo

引用次数: 4

Effects of temporal frequency on speed discrimination and perceived speed 时间频率对速度判别和感知速度的影响

Proceedings of the International Joint Conference on Neural Networks, 2003. Pub Date : 2003-07-20 DOI: 10.1109/IJCNN.2003.1223336

H. Shen, Y. Shimodaira, G. Ohashi

{"title":"Effects of temporal frequency on speed discrimination and perceived speed","authors":"H. Shen, Y. Shimodaira, G. Ohashi","doi":"10.1109/IJCNN.2003.1223336","DOIUrl":"https://doi.org/10.1109/IJCNN.2003.1223336","url":null,"abstract":"We examined the effects of temporal frequency of moving stimuli on speed discrimination and perceived speed in human vision, using psychophysical methods. A speed-comparing paradigm displaying two drifting sinusoidal luminance gratings simultaneously was adopted in our experiments. In experimental 1, human vision was found to be most sensitive to the speeds of moving gratings with temporal frequency of about 12 Hz, when speed was above 3.4 deg/sec. It suggests that a mechanism tuned to 12 Hz was involved in speed perception. In experiment 2, stimuli of subjectively equivalent speed (SSES) corresponding to various standard stimuli were determined in the frequency domain. The results showed that the distribution of SSES located along a straight line representing the physical speed of the standard stimuli at low standard speed in the frequency domain, which is considered as depart from the speed-tuning property. However, the distributions began to depart from the speed-tuning property and to approach a temporal-frequency-tuning property at higher speeds above 17 deg/sec. Our conclusion is that perceived speed and speed discrimination have speed-tuning property with normal speeds, but have a non-speed-tuning property with high speeds above 17 deg/sec; a mechanism tuned to 12 Hz is used by speed-tuned mechanisms and used directly by speed perception concurrently.","PeriodicalId":310128,"journal":{"name":"Proceedings of the International Joint Conference on Neural Networks, 2003.","volume":"14 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":"129777458","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

Evaluation of neural and entropy-constrained routing of communication networks 通信网络的神经和熵约束路由评价

Proceedings of the International Joint Conference on Neural Networks, 2003. Pub Date : 2003-07-20 DOI: 10.1109/IJCNN.2003.1223998

N. Karayiannis, S.M. Nagabhushan Kaliyur, H. Malki

引用次数: 1

An adaptive detection of anomalies in user's behavior 对用户行为异常的自适应检测

Proceedings of the International Joint Conference on Neural Networks, 2003. Pub Date : 2003-07-20 DOI: 10.1109/IJCNN.2003.1223947

A. Sokolov

引用次数: 3

A neurobiological theory of meaning in perception 关于感知意义的神经生物学理论

Proceedings of the International Joint Conference on Neural Networks, 2003. Pub Date : 2003-07-20 DOI: 10.1109/IJCNN.2003.1223896

Walter J. Freeman

{"title":"A neurobiological theory of meaning in perception","authors":"Walter J. Freeman","doi":"10.1109/IJCNN.2003.1223896","DOIUrl":"https://doi.org/10.1109/IJCNN.2003.1223896","url":null,"abstract":"The currency of brains is primarily meaning and only secondarily information. Brain select and pre-process the information carried by sensory stimuli before they construct meaning, and they post-process cognitive meaning into informative commands that control appropriate action and express meaning. A grasp of the intervening process of perception by which meaning is created from information requires observation of neural activity in brains during meaningful behavior of humans and other animals. Measurement is followed by detailed analysis and modeling of the neural activity in order to deduce brain dynamics from brain operations. Unlike computer operation, brain function is hierarchical with many levels. Neurobiologists infer sensory and motor information by recording pulses of microscopic axons of neurons. They infer meaning by recording the local mean fields that are generated by the dendrites of neurons forming interactive mesoscopic and macroscopic populations. Neural populations express meaning in spatial pattern of amplitude modulation of electroencephalographic (EEG) waveforms in the higher frequency ranges of cortical oscillations. Improved theory is needed to understand how brains create meaning. The aim of the theory is to apply population neurodynamics to device new ways to treat clinical brain disorders, and to devise new machines with capacities for autonomy and intelligence that might approach those of simpler free-living animals.","PeriodicalId":310128,"journal":{"name":"Proceedings of the International Joint Conference on Neural Networks, 2003.","volume":"16 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":"129676220","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: 104

A cascade form blind source separation connecting source separation and linearization for nonlinear mixtures 一种连接非线性混合源分离和线性化的级联形式盲源分离

Proceedings of the International Joint Conference on Neural Networks, 2003. Pub Date : 2003-07-20 DOI: 10.1109/IJCNN.2003.1223690

K. Nakayama, A. Hirano, Takayuki Nishiwaki

引用次数: 2

Parallel structured independent component analysis for SIMO-model-based blind separation and deconvolution of convolutive speech mixture 基于simo模型的卷积混合语音盲分离与反卷积并行结构独立分量分析

Proceedings of the International Joint Conference on Neural Networks, 2003. Pub Date : 2003-07-20 DOI: 10.1109/IJCNN.2003.1223456

H. Saruwatari, H. Yamajo, T. Takatani, T. Nishikawa, K. Shikano

{"title":"Parallel structured independent component analysis for SIMO-model-based blind separation and deconvolution of convolutive speech mixture","authors":"H. Saruwatari, H. Yamajo, T. Takatani, T. Nishikawa, K. Shikano","doi":"10.1109/IJCNN.2003.1223456","DOIUrl":"https://doi.org/10.1109/IJCNN.2003.1223456","url":null,"abstract":"We propose a two-stage blind separation and deconvolution (BSD) algorithm for a convolutive mixture of temporally correlated signals, in which a new single-input multiple-output (SIMO)-model-based ICA (SIMO-ICA) and blind multichannel inverse filtering are combined. SIMO-ICA consists of multiple ICAs and a fidelity controller, and each ICA runs in parallel under fidelity control of the entire separation system. SIMO-ICA can separate the mixed signals, not into monaural source signals but into SIMO-model-based signals from independent sources as they are at the microphones. After the separation by SIMO-ICA, a simple blind deconvolution technique based on multichannel inverse filtering for the SIMO model can be applied even when the mixing system is the nonminimum phase system and each source signal is temporally correlated. The experimental results obtained under the reverberant condition reveal that the sound quality of the separated signals in the proposed method is superior to that in the conventional ICA-based BSD.","PeriodicalId":310128,"journal":{"name":"Proceedings of the International Joint Conference on Neural Networks, 2003.","volume":"1 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":"129950645","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: 4

Invariant feature representation by sparse vectors using adaptive subspace self-organizing map 基于自适应子空间自组织映射的稀疏向量不变特征表示

Proceedings of the International Joint Conference on Neural Networks, 2003. Pub Date : 2003-07-20 DOI: 10.1109/IJCNN.2003.1223925

T. Zheng

引用次数: 1

Phoneme transcription based on Sampa for Norwegian 基于Sampa的挪威语音素转录

Proceedings of the International Joint Conference on Neural Networks, 2003. Pub Date : 2003-07-20 DOI: 10.1109/IJCNN.2003.1223450

T. Kristensen, B. Treeck, R. Falck-Olsen

引用次数: 4

Knowledge-oriented clustering for decision support 面向知识的聚类决策支持

Proceedings of the International Joint Conference on Neural Networks, 2003. Pub Date : 2003-07-20 DOI: 10.1109/IJCNN.2003.1224093

C. Bean, C. Kambhampati

引用次数: 4