IEEE International Joint Conference on Neural Network最新文献_第10页

Incremental Gain Analysis of Chaotic Recurrent Neural Network and Applications in Pattern Association 混沌递归神经网络的增量增益分析及其在模式关联中的应用

IEEE International Joint Conference on Neural Network Pub Date : 1900-01-01 DOI: 10.1109/IJCNN.2006.247357

Yilei Wu, Qinglin Song, Sheng Liu

引用次数: 0

Heterogeneous wireless networked control systems based on modify Smith predictor and CMAC-PID control 基于修正Smith预测器和CMAC-PID控制的异构无线网络控制系统

IEEE International Joint Conference on Neural Network Pub Date : 1900-01-01 DOI: 10.1109/IJCNN.2008.4634381

F. Du, Q. Qian

{"title":"Heterogeneous wireless networked control systems based on modify Smith predictor and CMAC-PID control","authors":"F. Du, Q. Qian","doi":"10.1109/IJCNN.2008.4634381","DOIUrl":"https://doi.org/10.1109/IJCNN.2008.4634381","url":null,"abstract":"The cerebellar model articulation controller (CMAC) neural network is a practical tool for improving existing nonlinear control systems, and it can effectively reduce tracking error of control system. In order to effectively restrain the impact of network delays for wireless networked control systems (WNCS), a novel approach is proposed that modified Smith predictor combined with CMAC-PID control for the heterogeneous wireless networked control systems (HWNCS). The HWNCS adopts cascade control system structure, use P control and CMAC-PID control, and data communications adopt heterogeneous wireless networks in the inner and outer loops. Based on modified Smith predictor, achieve complete compensations for the delays of networks and controlled plants. Because modified Smith predictor does not include network delay models, it is no need for measuring, identifying or estimating network delays on line. Therefore it is applicable to some occasions that network delays are larger than one, even tens of sampling periods. Based on IEEE 802.15.4 (ZigBee) in the inner loop and IEEE 802.11b/g (WLAN) in the outer loop, and there are data packets loss in the loops. The results of simulation show validity of the control scheme, and can improve dynamic performance, enhance robustness, self-adaptability and anti-jamming ability.","PeriodicalId":134599,"journal":{"name":"IEEE International Joint Conference on Neural Network","volume":"835 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124200624","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

The temporality of consciousness: Computational principles of a single information integration-propagation process (I2P2) 意识的时间性:单一信息整合-传播过程的计算原理(I2P2)

IEEE International Joint Conference on Neural Network Pub Date : 1900-01-01 DOI: 10.1109/IJCNN.2011.6033435

J. Sarrazin, V. González, B. Berberian, A. Tonnelier

{"title":"The temporality of consciousness: Computational principles of a single information integration-propagation process (I2P2)","authors":"J. Sarrazin, V. González, B. Berberian, A. Tonnelier","doi":"10.1109/IJCNN.2011.6033435","DOIUrl":"https://doi.org/10.1109/IJCNN.2011.6033435","url":null,"abstract":"Time plays a central role in consciousness. A crucial question is the following: Why Consciousness takes time? We suggest the contents of consciousness could emerge as the result of global competition biased by top-down (intentional) modulation, which implements global constraint satisfaction. In our simplified conceptual framework, the information integration and the consciousness are not implemented by separate processes but are unified through the idea that a network arrives at an interpretation of the input by converging towards a dynamical state, i.e. a recurring pattern related to the existence of a stable travelling wave. The synfire propagation can be recasted in this framework as a particular instance of conscious computation where (i) the network has a specialized topology (a chain of connected pools) and (ii) the sequence of spikes converge towards a synchronous spike volley. The framework we suggest has interesting connections with the neural processing proposed by Hopfield (1982) where the computation is achieved through the convergence of the dynamical system describing the neural network towards a fixed point. Here the attractors are correlated activities (or spatiotemporal periodic travelling waves) and the idea of associative memory can be generalized in this context.","PeriodicalId":134599,"journal":{"name":"IEEE International Joint Conference on Neural Network","volume":"7 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"120949566","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

Laser Cutting Parameters Optimization Based on Artificial Neural Network 基于人工神经网络的激光切割参数优化

IEEE International Joint Conference on Neural Network Pub Date : 1900-01-01 DOI: 10.1109/IJCNN.2006.246813

Dixin Guo, Jimin Chen, Yuhong Cheng

引用次数: 6

A Hybrid Character Representation for Chinese Event Detection 中文事件检测的混合字符表示

IEEE International Joint Conference on Neural Network Pub Date : 1900-01-01 DOI: 10.1109/IJCNN.2019.8851786

Xiangyu Xi, Tong Zhang, Wei Ye, Jinglei Zhang, Rui Xie, Shikun Zhang

{"title":"A Hybrid Character Representation for Chinese Event Detection","authors":"Xiangyu Xi, Tong Zhang, Wei Ye, Jinglei Zhang, Rui Xie, Shikun Zhang","doi":"10.1109/IJCNN.2019.8851786","DOIUrl":"https://doi.org/10.1109/IJCNN.2019.8851786","url":null,"abstract":"For the Chinese language, event triggers in a sentence may appear inside or across words after word segmentation. Thus recent works on Chinese event detection often formulate the task as a character-wise sequence labeling problem instead of a word-wise one. Due to a limited amount of corpus, however, it is more difficult in practice to train character-wise models to capture the inner structure of event triggers and the semantics of sentence-level context compared with word-wise ones. In this paper, we propose to improve character-wise models by incorporating word information and language model representation into Chinese character representation. More specifically, the former consists of the position of the character inside a word and the word’s embedding, which can aid structural pattern learning; the latter is obtained by BERT, which contains long-distance semantic information. We construct a sequence tagging model equipped with the hybrid representation and evaluate our model on ACE 2005 Chinese corpus. Experiment results show that both word information and language model representation are effective enhancements, and our model gains an increase of 4.5 (6.5%) and 6.1 (9.4%) in F1-score in event trigger identification task and classification task respectively over the state-of-the-art method.","PeriodicalId":134599,"journal":{"name":"IEEE International Joint Conference on Neural Network","volume":"75 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124197466","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: 14

A Reinforcement Learning Algorithm for Resource Provisioning in Mobile Edge Computing Network 移动边缘计算网络中资源分配的强化学习算法

IEEE International Joint Conference on Neural Network Pub Date : 1900-01-01 DOI: 10.1109/IJCNN48605.2020.9206947

Huynh Thi Thanh Binh, Phi-Le Nguyen, B. Nguyen, Trinh Thu Hai, Q. Ngo, D. Son

引用次数: 7

A Combined Fuzzy Clustering -Neuron Approach in the Segmentation of Non-uniform Color Surfaces 模糊聚类-神经元相结合的非均匀颜色曲面分割方法

IEEE International Joint Conference on Neural Network Pub Date : 1900-01-01 DOI: 10.1109/IJCNN.2007.4370960

M. Murguia, W. Perez-Regalado

{"title":"A Combined Fuzzy Clustering -Neuron Approach in the Segmentation of Non-uniform Color Surfaces","authors":"M. Murguia, W. Perez-Regalado","doi":"10.1109/IJCNN.2007.4370960","DOIUrl":"https://doi.org/10.1109/IJCNN.2007.4370960","url":null,"abstract":"Computational intelligence theories offer, individually, different potentials to solve real world problems. However, fusion of these potentials provides opportunities to generate more real world robust systems. Cosmetic inspection of possible non-uniform surfaces found in manufacturing is a challenge to human inspectors. This paper deals with the proposal of a new hybrid methodology to segment color images in order to detect non-uniform regions that may appear in manufactured goods. The hybrid methodology combines two fuzzy clustering algorithms, the FCM and the GG, and a SOM ANN. Because of its properties the FCM is used to find the optimal number of clusters of a sample population of nonuniform surfaces. This value is then used to initialize the GG algorithm to determine the best centroids that represents the color population. Finally a SOM is trained with the results of the GG to perform the segmentation. Findings show that the proposed methodology generates color regions in accordance to a quality inspection criterion. The proposed methodology is also compared against the performance of the FCM to show the advantages of the hybrid methodology.","PeriodicalId":134599,"journal":{"name":"IEEE International Joint Conference on Neural Network","volume":"117 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"117290890","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

Improving classification precision by implicit kernels motivated by manifold learning 基于流形学习的隐式核算法提高分类精度

IEEE International Joint Conference on Neural Network Pub Date : 1900-01-01 DOI: 10.1109/IJCNN.2006.246850

Yuexian Hou, Jingyi Wu, Pilian He

{"title":"Improving classification precision by implicit kernels motivated by manifold learning","authors":"Yuexian Hou, Jingyi Wu, Pilian He","doi":"10.1109/IJCNN.2006.246850","DOIUrl":"https://doi.org/10.1109/IJCNN.2006.246850","url":null,"abstract":"Recently several algorithms, e.g., Isomap, self-organizing isometric embedding (SIE), Locally linear embedding (LLE) and Laplacian eigenmap, were proposed to deal with the problem of learning low dimensional nonlinear manifold embedded in a high dimensional space. Motivated by these algorithms, there is a trend of exploiting the intrinsic manifold structure of the data to improve precision and/or efficiency of classification under the assumption that the high dimensional observable data resides on a low dimensional manifold of latten variables. But these methods suffer their flaws respectively. In this work, we unified the problems of supervised manifold learning in a kernel view and proposed a novel implicit kernel construction method, i. e. supervised locally principal direction preservation kernel (SLPDK) construction, to combine the advantages of current implicit kernel construction methods motivated by manifold learning and try to overcome their disadvantages. SLPDK uses class information and locally principal direction of manifold to implement an approximately symmetric embedding. Implicit kernels constructed by SLPDK have a natural geometrical explanation and can gain a considerable classification precision improvement when the condition of locally linear manifold separability (LLMS) holds.","PeriodicalId":134599,"journal":{"name":"IEEE International Joint Conference on Neural Network","volume":"12 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123822068","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

Semi-Supervised Multimodal Deep Learning Model for Polarity Detection in Arguments 参数极性检测的半监督多模态深度学习模型

IEEE International Joint Conference on Neural Network Pub Date : 1900-01-01 DOI: 10.1109/IJCNN.2018.8489342

A. Tato, R. Nkambou, A. Dufresne, C. Frasson

{"title":"Semi-Supervised Multimodal Deep Learning Model for Polarity Detection in Arguments","authors":"A. Tato, R. Nkambou, A. Dufresne, C. Frasson","doi":"10.1109/IJCNN.2018.8489342","DOIUrl":"https://doi.org/10.1109/IJCNN.2018.8489342","url":null,"abstract":"Deep learning has been successfully applied to many tasks such as image classification, feature learning, Text classification (sentiments analysis or opinion mining) etc. However, little research has focused on extracting polarity of sentiments expressed in text using a multimodal architecture. In other words, no researches take in consideration the multimodal nature of human behaviors before classifying sentiments. The representation of a person (also call User Modeling in some domains such as Intelligent Tutoring Systems) is an important feature to take in consideration if one wants to extract subjective information such as the polarity of sentiments expressed by the person. To design an effective representation of a user, it is important to consider all sources of data informing about its current state. We present a usersensitive deep multimodal architecture which takes advantage of deep learning and user data to extract a rich latent representation of a user. This rich latent representation mainly helps in text classification tasks. The architecture consists of the combination of a Long Short-Term Memory (LSTM), LSTM-Auto-Encoder, Convolutional Neural Networks and multiple Deep Neural Networks, in order to support the multimodality of data. The resulting model has been tested on a public multimodal dataset and is able to achieve best results compared to state-of-the-art algorithms for a similar task: detection of opinion polarity. The results suggest that the latent representation learnt from multimodal data helps in the discrimination of polarity of opinion.","PeriodicalId":134599,"journal":{"name":"IEEE International Joint Conference on Neural Network","volume":"22 4","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"120899714","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: 6

Associative-memory-recall-based control system for learning hovering manoeuvres 基于联想记忆的悬停动作学习控制系统

IEEE International Joint Conference on Neural Network Pub Date : 1900-01-01 DOI: 10.1109/IJCNN.2015.7280554

Pei-Hua Huang, O. Hasegawa

{"title":"Associative-memory-recall-based control system for learning hovering manoeuvres","authors":"Pei-Hua Huang, O. Hasegawa","doi":"10.1109/IJCNN.2015.7280554","DOIUrl":"https://doi.org/10.1109/IJCNN.2015.7280554","url":null,"abstract":"This study presents a robotic application of neural associative memory-based control system that imparts online learning and predictive control strategies to a cost-effective quadrotor helicopter, the Parrot AR.Drone 2.0. The control system is extended with to tackle a fundamental and challenging problem for the quadcoptor: hovering control. The proposed system is based on self-organizing incremental neural network that includes an associative memory algorithm. The algorithm can cope with a hierarchical data space and complex time-transition dynamics; it enables online incremental learning from manual control, thereby gradually improve the stability against interference such as drift caused by either mechanical impairment or external excitation. In particular, after continuously learning the associative state-command pair of hovering manoeuvre, the system can execute the command associated with current state. The proposed system is evaluated on a realistic AR.Drone quadcoptor to test its capacity to tackle the hovering control problem. The results demonstrate that for the first time, the proposed system effectively offers a novel approach to quadcoptor application of an associative memory-based neural network by successfully tackling a hover task through iterative on-line learning.","PeriodicalId":134599,"journal":{"name":"IEEE International Joint Conference on Neural Network","volume":"2 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124555074","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