Proceedings. 2005 IEEE International Joint Conference on Neural Networks, 2005.最新文献_第7页

Negative reinforcement and backtrack-points for recurrent neural networks for cost-based abduction 基于成本的溯及性递归神经网络的负强化和回溯点

Proceedings. 2005 IEEE International Joint Conference on Neural Networks, 2005. Pub Date : 2005-12-27 DOI: 10.1109/IJCNN.2005.1555959

A. M. Abdelbar, M. A. El-Hemaly, Emad Andrews, D. Wunsch

{"title":"Negative reinforcement and backtrack-points for recurrent neural networks for cost-based abduction","authors":"A. M. Abdelbar, M. A. El-Hemaly, Emad Andrews, D. Wunsch","doi":"10.1109/IJCNN.2005.1555959","DOIUrl":"https://doi.org/10.1109/IJCNN.2005.1555959","url":null,"abstract":"Abduction is the process of proceeding from data describing a set of observations or events, to a set of hypotheses which best explains or accounts for the data. Cost-based abduction (CKA) is an AI formalism in which evidence to be explained is treated as a goal to be proven, proofs have costs based on how much needs to be assumed to complete the proof, and the set of assumptions needed to complete the least-cost proof are taken as the best explanation for the given evidence. In this paper, we introduce two techniques for improving the performance of high order recurrent networks (HORN) applied to cost-based abduction. In the backtrack-points technique, we use heuristics to recognize early that the network trajectory is moving in the wrong direction; we then restore the network state to a previously-stored point, and apply heuristic perturbations to nudge the network trajectory in a different direction. In the negative reinforcement technique, we add hyperedges to the network to reduce the attractiveness of local-minima. We apply these techniques on a 300-hypothesis, 900-rule particularly-difficult instance of CBA.","PeriodicalId":365690,"journal":{"name":"Proceedings. 2005 IEEE International Joint Conference on Neural Networks, 2005.","volume":"94 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2005-12-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123715246","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

Harmonic envelope prediction for realistic speech synthesis using kernel interpolation 基于核插值的现实语音合成谐波包络预测

Proceedings. 2005 IEEE International Joint Conference on Neural Networks, 2005. Pub Date : 2005-12-27 DOI: 10.1109/IJCNN.2005.1556217

P.-A. Fournier, Jean-Jules Brault

引用次数: 0

Knowing your place: subfield specific involvement in hippocampal spatial processing 知道你的位置:海马体空间处理的子场特定参与

Proceedings. 2005 IEEE International Joint Conference on Neural Networks, 2005. Pub Date : 2005-12-27 DOI: 10.1109/IJCNN.2005.1556382

M. Hartley, Neil Taylor, John Taylor

引用次数: 1

Random projections for assessing gene expression cluster stability 评估基因表达簇稳定性的随机投影

Proceedings. 2005 IEEE International Joint Conference on Neural Networks, 2005. Pub Date : 2005-12-27 DOI: 10.1109/IJCNN.2005.1555821

A. Bertoni, G. Valentini

引用次数: 32

A model of Baldwin effect in populations of self-learning agents 自学习主体群体中的Baldwin效应模型

Proceedings. 2005 IEEE International Joint Conference on Neural Networks, 2005. Pub Date : 2005-12-27 DOI: 10.1109/IJCNN.2005.1556071

V. Red'ko, O. P. Mosalov, D. Prokhorov

引用次数: 5

Are ARIMA neural network hybrids better than single models? ARIMA神经网络混合模型比单一模型更好吗?

Proceedings. 2005 IEEE International Joint Conference on Neural Networks, 2005. Pub Date : 2005-12-27 DOI: 10.1109/IJCNN.2005.1556438

T. Taşkaya-Temizel, Khurshid Ahmad

引用次数: 27

An experimental study of several decision issues for feature selection with multi-layer perceptrons 多层感知器特征选择决策问题的实验研究

Proceedings. 2005 IEEE International Joint Conference on Neural Networks, 2005. Pub Date : 2005-12-27 DOI: 10.1109/IJCNN.2005.1556181

E. Romero, J. Sopena

引用次数: 0

Atmospheric correction and oceanic constituents retrieval, with a neuro-variational method 基于神经变分方法的大气校正与海洋成分检索

Proceedings. 2005 IEEE International Joint Conference on Neural Networks, 2005. Pub Date : 2005-12-27 DOI: 10.1109/IJCNN.2005.1556121

J. Brajard, S. Thiria, C. Jamet, C. Moulin

{"title":"Atmospheric correction and oceanic constituents retrieval, with a neuro-variational method","authors":"J. Brajard, S. Thiria, C. Jamet, C. Moulin","doi":"10.1109/IJCNN.2005.1556121","DOIUrl":"https://doi.org/10.1109/IJCNN.2005.1556121","url":null,"abstract":"Ocean color sensors on board satellite measure the solar radiation reflected by the ocean and the atmosphere. This information, denoted reflectance, is affected for 90% by air molecules and aerosols in the atmosphere and for only 10% by water molecules and phytoplankton cells in the ocean. Our method focuses on the chlorophyll-a concentration (chl-a) retrieval, which is commonly used as a proxy for phytoplankton concentration. Our algorithm, denoted NeuroVaria, computes relevant atmospheric (Angstrom coefficient, optical thickness, single-scattering albedo) and oceanic parameters (chl-a, oceanic particulate scattering) by minimizing the difference over the whole spectrum (visible + near infrared) between the observed reflectance and the reflectance computed from artificial neural networks that have been learned with a radiative transfer model. NeuroVaria has been applied to SeaWiFS (sea-viewing wide field-of-view sensor) imagery in the Mediterranean sea. A comparison with in-situ measurements of the water-leaving reflectance shows that NeuroVaria enables to better reconstruct this component at 443 nm than the standard SeaWiFS processing. This leads to an improvement of the retrieval of the chl-a for the oligotrophic sea. This result is generalized to the entire Mediterranean sea through weekly maps of chl-a.","PeriodicalId":365690,"journal":{"name":"Proceedings. 2005 IEEE International Joint Conference on Neural Networks, 2005.","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2005-12-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126791375","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

A research on combination methods for ensembles of multilayer feedforward 多层前馈系统集成组合方法研究

Proceedings. 2005 IEEE International Joint Conference on Neural Networks, 2005. Pub Date : 2005-12-27 DOI: 10.1109/IJCNN.2005.1556011

J. Torres-Sospedra, M. Fernández-Redondo, C. Hernández-Espinosa

引用次数: 16

A digital LSI architecture of elastic graph matching and its FPGA implementation 弹性图匹配的数字大规模集成电路结构及其FPGA实现

Proceedings. 2005 IEEE International Joint Conference on Neural Networks, 2005. Pub Date : 2005-12-27 DOI: 10.1109/IJCNN.2005.1555935

T. Nakano, T. Morie

引用次数: 9