检索结果-内蒙古大学图书馆

arXiv 2017年

作者： Cai, Cheng-Hao Ke, Dengfeng Xu, Yanyan Su, Kaile National Laboratory of Pattern Recognition Institute of Automation Chinese Academy of Sciences School of Information Science and Technology Beijing Forestry University Institute for Integrated and Intelligent Systems Griffith University

There is a wide gap between symbolic reasoning and deep learning. In this research, we explore the possibility of using deep learning to improve symbolic reasoning. Briefly, in a reasoning system, a deep feedforward neural network is used to guide rewriting processes after learning from algebraic reasoning examples produced by humans. To enable the neural network to recognise patterns of algebraic expressions with non-deterministic sizes, reduced partial trees are used to represent the expressions. Also, to represent both top-down and bottom-up information of the expressions, a centralisation technique is used to improve the reduced partial trees. Besides, symbolic association vectors and rule application records are used to improve the rewriting processes. Experimental results reveal that the algebraic reasoning examples can be accurately learnt only if the feedforward neural network has enough hidden layers. Also, the centralisation technique, the symbolic association vectors and the rule application records can reduce error rates of reasoning. In particular, the above approaches have led to 4.6% error rate of reasoning on a dataset of linear equations, differentials and integrals. Copyright © 2017, The Authors. All rights reserved.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

Neural network structure design based on N-gauss activation function1

arXiv

引用

arXiv 2021年

作者： Lu, Xiangri Ma, Hongbin Zhang, Jingcheng State Key Laboratory of Intelligent Decision and Control for Complex Systems Beijing Institute ofTechnology Beijing China Institute of Pattern Recognition and Intelligent Systems School of Automation Beijing Institute ofTechnology China Institute of Navigation Guidance and Control School of Automation Beijing Institute of

Recent work has shown that the activation function of the convolutional neural network can meet the Lipschitz condition, then the corresponding convolutional neural network structure can be constructed according to the scale of the data set, and the data set can be trained more deeply, more accurately and more effectively. In this article, we have accepted the experimental results and introduced the core block N − Gauss, N − Gauss, and Swish (Conv1, Conv2, FC1) neural network structure design to train MNIST, CIFAR10, and CIFAR100 respectively. Experiments show that N − Gauss gives full play to the main role of nonlinear modeling of activation functions, so that deep convolutional neural networks have hierarchical nonlinear mapping learning capabilities. At the same time, the training ability of N − Gauss on simple one-dimensional channel small data sets is equivalent to the performance of ReLU and Swish. Copyright © 2021, The Authors. All rights reserved.

关键词： Gaussian distribution

来源：评论

学校读者我要写书评

暂无评论

Lip Localization on Multi-View Faces in Video

Lip Localization on Multi-View Faces in Video

引用

IEEE International Conference on Multimedia and Expo (ICME)

作者： Rui Ma Yi Wu Wei Hu Jiaxin Wang Tao Wang Yimin Zhang Hanqing Lu State Key Laboratory of Intelligent Technology and Systems Tsinghua University Beijing China National Laboratory of Pattern Recognition Institute of Automation Chinese Academy and Sciences China Intel China Research Center Limited Beijing China

In this paper, a real time and robust multi-view lip localization in video frames is proposed. The objective of this research is to exactly localize lip surrounding box with sub-pixel accuracy in low quality video frames. This is achieved by multi-view face detection in video frames, lip ROI extraction, color space transformation, vertical edge feature detection and lip localization by a feature-spatial profile analysis on a joint color-edge plane. One possible application of talking face detection in video is used to evaluate our work. Experimental results on TV programs and movies demonstrate that the proposed approach is efficient and robust in lip localization.

关键词： Face detection Skin Robustness TV Lips Laboratories Motion pictures Image quality Image segmentation Head

来源：评论

学校读者我要写书评

暂无评论

Slow Feature Analysis for Human Action recognition

arXiv

引用

arXiv 2019年

作者： Zhang, Zhang Tao, Dacheng National Laboratory of Pattern Recognition Institute of Automation Chinese Academy of Sciences P.R China Centre for Quantum Computation and Intelligent Systems Faculty of Engineering and Information Technology University of Technology Sydney Australia

Slow Feature Analysis (SFA) extracts slowly varying features from a quickly varying input signal [1]. It has been successfully applied to modeling the visual receptive fields of the cortical neurons. Sufficient experimental results in neuroscience suggest that the temporal slowness principle is a general learning principle in visual perception. In this paper, we introduce the SFA framework to the problem of human action recognition by incorporating the discriminative information with SFA learning and considering the spatial relationship of body parts. In particular, we consider four kinds of SFA learning strategies, including the original unsupervised SFA (U-SFA), the supervised SFA (S-SFA), the discriminative SFA (D-SFA), and the spatial discriminative SFA (SD-SFA), to extract slow feature functions from a large amount of training cuboids which are obtained by random sampling in motion boundaries. Afterward, to represent action sequences, the squared first order temporal derivatives are accumulated over all transformed cuboids into one feature vector, which is termed the Accumulated Squared Derivative (ASD) feature. The ASD feature encodes the statistical distribution of slow features in an action sequence. Finally, a linear support vector machine (SVM) is trained to classify actions represented by ASD features. We conduct extensive experiments, including two sets of control experiments, two sets of large scale experiments on the KTH and Weizmann databases, and two sets of experiments on the CASIA and UT-interaction databases, to demonstrate the effectiveness of SFA for human action recognition. Experimental results suggest that the SFA-based approach 1) is able to extract useful motion patterns and improves the recognition performance, 2) requires less intermediate processing steps but achieves comparable or even better performance, and 3) has good potential to recognize complex multiperson activities. Copyright © 2019, The Authors. All rights reserved.

关键词： Support vector machines

来源：评论

学校读者我要写书评

暂无评论

A Generalized Denoising Method with an Optimized Loss Function for Automated Bird Sound recognition

A Generalized Denoising Method with an Optimized Loss Functi...

引用

International Conference on Computers, Communications, and systems (ICCCS)

作者： Huangqiang Fang Yulin He Wanyang Xu Yanyan Xu Dengfeng Ke Kaile Su School of Information Science and Technology Beijing Forestry University Beijing China National Laboratory of Pattern Recognition Institute of Automation Chinese Academy of Sciences Beijing China Institute for Integrated and Intelligent Systems Griffith University Nathan Australia

ISBN: (数字)9781728161365

ISBN: (纸本)9781728161372

In natural environments, bird sounds are often accompanied by background noise, so denoising becomes crucial to automated bird sound recognition. Recently, thanks to neural network embeddings, the deep clustering method has achieved better performances than traditional denoising methods, like filter-based methods, due to its ability to solve the problem when noise is in the same frequency range as bird sounds. In this paper, we propose a generalized denoising method based on deep clustering, which can process more complex recordings with less distortion. Also, we optimize the original affinity loss function to get a novel loss function to ensure the embedding vectors with the minimum distance belong to the same source, named Joint Center Loss (JCL), which can both increase the inter-class variance and decrease the intra-class variance of embeddings. Experiments are conducted on the gated convolutional neural network architecture and the bidirectional long short term memory architecture respectively with different loss functions. Given the signal-noise ratio being -3dB, the recognition accuracy increases relatively by 9.5% with the proposed denoising method in the best case, and the Relative Root Mean Square Error (RRMSE) increases relatively by 14.2% by using JCL, compared with the original affinity loss function AL.

关键词： Birds Noise reduction Logic gates Training Noise measurement Time-frequency analysis Matrix converters

来源：评论

学校读者我要写书评

暂无评论

Analysis of Key Factors in Heat Demand Prediction with Neural Networks

引用

Energy Procedia 2017年 105卷 2965-2970页

作者： Jiyang Xie Hailong Li Zhanyu Ma Qie Sun Fredrik Wallin Zhongwei Si Jun Guo Pattern Recognition and Intelligent Systems Lab. Beijing University of Posts and Telecommunications China School of Business Society and Engineering Mälardalen University Sweden Institute of Thermal Science and Technology Shandong University China Key Laboratory of Universal Wireless Communications Ministry of Education Beijing University of Posts and Telecommunications China

The development of heat metering has promoted the development of statistic models for the prediction of heat demand, due to the large amount of available data, or big data. Weather data have been commonly used as input in such statistic models. In order to understand the impacts of direct solar radiance and wind speed on the model performance comprehensively, a model based on Elman neural networks (ENN) was adopted, of which the results can help heat producers to optimize their production and thus mitigate costs. Compared with the measured heat demand, the introduction of wind speed and direct solar radiation has opposite impacts on the performance of ENN and the inclusion of wind speed can improve the prediction accuracy of ENN. However, ENN cannot benefit from the introduction of both wind speed and direct solar radiation simultaneously.

关键词： District heating data processing prediction heat demand CHP plant

来源：评论

学校读者我要写书评

暂无评论

Gait Planning and Motion Control Based on Vrep Simulation for Quadruped Robot

Gait Planning and Motion Control Based on Vrep Simulation fo...

引用

WRC Symposium on Advanced Robotics and Automation (WRC SARA)

作者： Linqi Zhou Zhihua Chen Jun Liu Zhi Liu Yumeng Chen Liting Zhang key Laboratory of Jiangxi Province for Image Processing and Pattern Recognition and MOE Key Lab of Nondestructive Testing Technology Nanchang Hangkong University Nanchang China State Key Laboratory of Intelligent Control and Decision of Complex Systems School of Automation Beijing Institute of Technology Beijing China

Gait planning of quadruped robots plays an important role in achieving less walking, including dynamic and static gait. In this article, a static and dynamic gait control method based on center of gravity stability margin is proposed. Firstly, the robot model and kinematics modeling are introduced. Secondly, the robot’s foot static and dynamic gait were planned and the foot trajectory was designed. Finally, two types of gait of the robot were simulated using Vrep simulation software, and the differences in stability and speed between the coordinated gait with speed and stability in the static and dynamic gait of a 12 degree of freedom robot were analyzed, verifying the effectiveness of the gait control method proposed in this paper.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Research on the Parameter Optimal Algorithm of Gaussian Mixture Model in Speaker Identification

Research on the Parameter Optimal Algorithm of Gaussian Mixt...

引用

Chinese Conference on pattern recognition (CCPR)

作者： Hui Ding Zhenmin Tang Yanping Li Laboratory of Pattern Recognition and Intelligent Systems Nanjing University of Science and Technology of PLA Nanjing Jiangsu China School of Mathematics & Information Engineering Jiaxing University Jiaxing Zhejiang China College of Telecommunications & Information Engineering Nanjing University of Posts and Telecommunications China

In the field of speaker recognition, the Gaussian mixture model with diagonal covariance matrices is a popular technique, in this way, it simplified model and reduced the amount of computation, but lost the correlation information between feature vectors, and then influenced the classification performance. In this paper, in order to compensate the correlation between feature elements, we proposed a novel method based on clustering transformation algorithm, we calculate the similarity between Gaussian components, and the cluster of same components will share one transformation matrix, thus multi-transformation matrices, together with weights and means vectors are obtained simultaneously by maximum likelihood estimation. Theory analysis and experimental results demonstrated that this proposed method can get a better balance between training speed and recognition rate, improve the performance of classifier and reduce the complexity and memory burden relatively.

关键词： Electronic mail Covariance matrix Laboratories pattern recognition intelligent systems Mathematics Educational institutions Speaker recognition Telecommunication computing Clustering algorithms

来源：评论

学校读者我要写书评

暂无评论

MiSiM:Microstructured Fibers' Simulator

MiSiM:Microstructured Fibers' Simulator

引用

Latin American Electron Devices Conference (LAEDC)

作者： Paola Montero-Sánchez Ricardo Román-Brenes F. Siles Jaime Cascante-Vindas LAFTLA: Laboratorio de Fotónica y Tecnología Láser Aplicada Universidad de Costa Rica San José Costa Rica PRIS-Lab: Pattern Recognition and Intelligent Systems Laboratory Universidad de Costa Rica San José Costa Rica

ISBN: (数字)9781728110448

ISBN: (纸本)9781728110455

In this work we present MISIM: a free and open software tool for the simulation of microstructured fibers, that can be used for the calculation of their dispersion profiles, for its design and posterior manufacturing. The software is based on the numerical model of Saitoh and Koshiba, and it is able to simulate chromatic dispersion, effective index and group index for a given spectral range. MISIM generates output text files as well as line charts of the simulated parameters. As far as we known, it is the only open and free software with a GUI that can visualize its output directly. For the validation of the tool, results from MISIM were compared with those reported in the literature using different methods to calculate their profiles, obtaining, for example effective indexes within one standard deviation of those reported. Even smaller errors (2.61%) were obtained for the chromatic dispersion using our proposed tool.

关键词： Software Indexes Chromatic dispersion Mathematical model Tools Graphical user interfaces

来源：评论

学校读者我要写书评

暂无评论

Video vehicle detection through multiple background-based features and statistical learning

Video vehicle detection through multiple background-based fe...

引用

International Conference on intelligent Transportation

作者： Mingxia Sun Kunfeng Wang Ming Tang Fei-Yue Wang Jinfeng Yang Tianjin Key Laboratory of Advanced Signal Processing Civil Aviation University of China Tianjin China State Key Laboratory of Intelligent Control and Management of Complex Systems Institute of Automation Chinese Academy of Sciences (CAS) Beijing China National Laboratory of Pattern Recognition Institute of Automation Chinese Academy of Sciences (CAS) Beijing China

This paper presents a generic video vehicle detection approach through multiple background-based features and statistical learning. The main idea is to configure several virtual loops (as detection zones) on the image, assuming moving vehicles may cause pixel intensities and local texture to change, and then by identifying such pixel changes to detect vehicles. In this research, multiple pattern classifiers including LDA + Adaboost, SVM, and Random Forests are used to detect vehicles that are passing through virtual loops. We extract fourteen pattern features (related to foreground area, texture change, and luminance and contrast in the local virtual loop zone and the global image) to train pattern classifiers and then detect vehicles. As experimental results illustrate, the proposed approach is quite robust to detect vehicles under complex dynamic environments, and thus is able to improve the accuracy of traffic data collection in all weather for long term.

关键词： Vehicles Feature extraction Training Image edge detection Vehicle detection Meteorology Radio frequency

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：