检索结果-内蒙古大学图书馆

International Journal of Internet Manufacturing and Services

作者： Wu, Shaochun Gao, Ming Xiao, Qifeng Zou, Guobing Department of Intelligent Information Processing Shanghai University Shanghai200444 China

This paper presents a topic-enhanced recurrent autoencoder model to improve the accuracy of sentiment classification of short texts. First, the concept of recurrent autoencoder is proposed to tackle the problems in recursive autoencoder including 'increasing in computation complexity' and 'ignoring the natural word order'. Then, the recurrent autoencoder model is enhanced with the topic and sentiment information generated by joint sentiment-topic (JST) model. Besides, in order to identify the negations and ironies in short texts, sentiment lexicon is utilised to add feature dimensions for sentence representations. Experiments are performed to determine the feasibility and effectiveness of the model. Compared with recursive autoencoder model, the classification accuracy of our model is improved by about 7.7%. © 2020 Inderscience Enterprises Ltd.

关键词： Learning systems Sentiment analysis Auto encoders Classification accuracy computation complexity Feature dimensions Joint sentiment topic (JST) model Natural words Sentiment classification Sentiment lexicons

来源：评论

学校读者我要写书评

暂无评论

On the convergence and improvement of stochastic normalized gradient descent

引用

Science China(Information Sciences) 2021年第3期64卷 105-117页

作者： Shen-Yi ZHAO Yin-Peng XIE Wu-Jun LI National Key Laboratory for Novel Software Technology Department of Computer Science and TechnologyNanjing University

Non-convex models, like deep neural networks, have been widely used in machine learning applications. Training non-convex models is a difficult task owing to the saddle points of models. Recently,stochastic normalized gradient descent(SNGD), which updates the model parameter by a normalized gradient in each iteration, has attracted much attention. Existing results show that SNGD can achieve better performance on escaping saddle points than classical training methods like stochastic gradient descent(SGD).However, none of the existing studies has provided theoretical proof about the convergence of SNGD for non-convex problems. In this paper, we firstly prove the convergence of SNGD for non-convex ***, we prove that SNGD can achieve the same computation complexity as SGD. In addition, based on our convergence proof of SNGD, we find that SNGD needs to adopt a small constant learning rate for convergence guarantee. This makes SNGD do not perform well on training large non-convex models in practice. Hence, we propose a new method, called stagewise SNGD(S-SNGD), to improve the performance of SNGD. Different from SNGD in which a small constant learning rate is necessary for convergence guarantee,S-SNGD can adopt a large initial learning rate and reduce the learning rate by stage. The convergence of S-SNGD can also be theoretically proved for non-convex problems. Empirical results on deep neural networks show that S-SNGD achieves better performance than SNGD in terms of both training loss and test accuracy.

关键词： non-convex problems stochastic normalized gradient descent computation complexity

来源：评论

学校读者我要写书评

暂无评论

A 2.4kbps MBE-LPC speech codec algorithm suitable for VLSI implementation

A 2.4kbps MBE-LPC speech codec algorithm suitable for VLSI i...

引用

2nd International Conference on ASIC

作者： Yang, HM Chen, HY Sun, YH The Institute of Microelectronics Tsinghua University Beijing China

ISBN: (纸本)7543909405

A speech code/decode algorithm which combines MBE and LPC speech model is proposed. In this model, the spectral envelope is represented using Linear Prediction Coefficients, which are coded using Line Spectrum Frequencies (LSFs). It can operate at 2.4 kbps with much higher quality of synthesis speech than LPC-10e and less computation complexity than CELP, VSELP and so on. Therefore it is particularly attractive for VLSI implementation.

关键词： speech codecs VLSI linear predictive coding computational complexity speech codec algorithm VLSI implementation MBE LPC spectral envelope linear prediction coefficients line spectrum frequencies computation complexity multiband excitation 2.4 kbit/s

来源：评论

学校读者我要写书评

暂无评论

Fast and robust adaptive beamforming algorithms for large-scale arrays with small samples

引用

SIGNAL PROCESSING 2021年 188卷 108223-108223页

作者： Zhang, Xue-Jun Xie, Hu Feng, Da-Zheng Zheng, Wei Xing Hu, Hao Shuang Xidian Univ Natl Lab Radar Signal Proc Xian 710071 Peoples R China Univ Western Sydney Sch Comp Engn & Math Penrith NSW 1797 Australia

The adaptive beamformer of large-scale sensor array mainly suffers from two limits. One limit is an insufficient number of training snapshots, which usually results in an ill-posed sample covariance matrix in many real applications. The other limit is the high computation complexity of the beamformer that severely restricts its online processing. To overcome these two limits, two fast and robust adaptive beam forming algorithms are proposed in this paper, which refers to the linear kernel approaches and formulates the weight vector as a linear combination of the training samples and the signal steering vector. The proposed algorithms only need to calculate a low-dimensional combination vector instead of the high-dimensional adaptive weight vector, which remarkably reduces the computation complexity. Moreover, regularization techniques are utilized to suppress the excessive variation of the combination vector caused by an underdetermined estimation of the Gram matrix. Experimental results show that the proposed algorithms achieve better performance and lower computation complexity than algorithms in the literature. Especially, like the kernel approaches, the proposed algorithms achieve good performance under the small sample case.& nbsp;(c) 2021 Published by Elsevier B.V.

关键词： Adaptive beamforming algorithm Large-scale sensor array computation complexity Regularization technique Linear kernel approach

来源：评论

学校读者我要写书评

暂无评论

Approximating the Partition Function of the Ferromagnetic Potts Model

引用

JOURNAL OF THE ACM 2012年第5期59卷 25-25页

作者： Goldberg, Leslie Ann Jerrum, Mark Univ Liverpool Dept Comp Sci Liverpool L69 3BX Merseyside England Univ London Sch Math Sci London E1 4NS England

We provide evidence that it is computationally difficult to approximate the partition function of the ferromagnetic q-state Potts model when q > 2. Specifically, we show that the partition function is hard for the complexity class #RH Pi(1) under approximation-preserving reducibility. Thus, it is as hard to approximate the partition function as it is to find approximate solutions to a wide range of counting problems, including that of determining the number of independent sets in a bipartite graph. Our proof exploits the first-order phase transition of the "random cluster" model, which is a probability distribution on graphs that is closely related to the q-state Potts model.

关键词： Theory Approximation algorithms computation complexity phase transition Potts model random cluster model statistical physics Tutte polynomial

来源：评论

学校读者我要写书评

暂无评论

Matching Theory for Channel Allocation in Cognitive Radio Networks

Matching Theory for Channel Allocation in Cognitive Radio Ne...

引用

作者： Cao, L. Brno University of Technology

For a cognitive radio network (CRN) in which a set of secondary users (SUs) competes for a limited number of channels (spectrum resources) belonging to primary users (PUs), the channel allocation is a challenge and dominates the throughput and congestion of the network. In this paper, the channel allocation problem is first formulated as the 0-1 integer programming optimization, with considering the overall utility both of primary system and secondary system. Inspired by matching theory, a many-to-one matching game is used to remodel the channel allocation problem, and the corresponding PU proposing deferred acceptance (PPDA) algorithm is also proposed to yield a stable matching. We compare the performance and computation complexity between these two solutions. Numerical results demonstrate the efficiency and obtain the communication overhead of the proposed scheme.

关键词： cognitive radio channel allocation optimization matching theory stable matching computation complexity

来源：评论

学校读者我要写书评

暂无评论

IIRNet: A lightweight deep neural network using intensely inverted residuals for image recognition

引用

IMAGE AND VISION COMPUTING 2019年 92卷 103819-000页

作者： Li, Yuyuan Zhang, Dong Lee, Dah-Jye Sun Yat Sen Univ Sch Elect & Informat Technol Guangzhou Guangdong Peoples R China Sun Yat Sen Univ Shunde Res Inst Shunde Foshan Peoples R China Brigham Young Univ Dept Elect & Comp Engn Provo UT 84602 USA

Deep neural networks have achieved great success in many tasks of pattern recognition. However, large model size and high cost in computation limit their applications in resource-limited systems. In this paper, our focus is to design a lightweight and efficient convolutional neural network architecture by directly training the compact network for image recognition. To achieve a good balance among classification accuracy, model size, and computation complexity, we propose a lightweight convolutional neural network architecture named IIRNet for resource-limited systems. The new architecture is built based on Intensely Inverted Residual block (IIR block) to decrease the redundancy of the convolutional blocks. By utilizing two new operations, intensely inverted residual and multi-scale low-redundancy convolutions, IIR block greatly reduces its model size and computational costs while matches the classification accuracy of the state-of-the-art networks. Experiments on CIFAR-10, CIFAR-100, and ImageNet datasets demonstrate the superior performance of IIRNet on the trade-offs among classification accuracy, computation complexity, and model size, compared to the mainstream compact network architectures. (C) 2019 Elsevier B.V. All rights reserved.

关键词： Convolutional neural network (CNN) Lightweight CNN Image recognition Low-redundancy Model size computation complexity

来源：评论

学校读者我要写书评

暂无评论

P1DSOM-A FAST SEARCH ALGORITHM FOR HIGH-DIMENSIONAL FEATURE SPACE PROBLEMS

引用

INTERNATIONAL JOURNAL OF PATTERN RECOGNITION AND ARTIFICIAL INTELLIGENCE 2014年第2期28卷 1459005-1459005页

作者： Sagheer, Alaa Tsuruta, Nayouki Taniguchi, Rin-Ichiro Aswan Univ Dept Math Ctr Artificial Intelligence & RObot CAIRO Aswan Egypt Fukuoka Univ Dept Elect Engn & Comp Sci Fukuoka Japan Kyushu Univ Dept Adv Informat Technol Fukuoka 812 Japan

The self-organizing map (SOM) is a traditional neural network algorithm used to achieve feature extraction, clustering, visualization and data exploration. However, it is known that the computational cost of the traditional SOM, used to search for the winner neuron, is expensive especially in case of treating high-dimensional data. In this paper, we propose a novel hierarchical SOM search algorithm which significantly reduces the expensive computational cost associated with traditional SOM. It is shown here that the computational cost of the proposed approach, compared to traditional SOM, to search for the winner neuron is reduced into O(D-1 + D-2 + . . . + D-N) instead of O(D-1 x D-2 x . . . x D-N), where D-j is the number of neurons through a dimension d(j) of the feature map. At the same time, the new algorithm maintains all merits and qualities of the traditional SOM. Experimental results show that the proposed algorithm is a good alternate to traditional SOM, especially, in high-dimensional feature space problems.

关键词： Self-organizing maps principal rows analysis computation complexity face feature extraction face recognition

来源：评论

学校读者我要写书评

暂无评论

Feasibility of a Real-Time Embedded Hyperspectral Compressive Sensing Imaging System

引用

SENSORS 2022年第24期22卷 9793页

作者： Lim, Olivier Mancini, Stephane Dalla Mura, Mauro Univ Grenoble Alpes CNRS Grenoble INP TIMA F-38031 Grenoble France Univ Grenoble Alpes GIPSA Lab CNRS Grenoble INP F-38000 Grenoble France Inst Univ France IUF F-75231 Paris France

Hyperspectral imaging has been attracting considerable interest as it provides spectrally rich acquisitions useful in several applications, such as remote sensing, agriculture, astronomy, geology and medicine. Hyperspectral devices based on compressive acquisitions have appeared recently as an alternative to conventional hyperspectral imaging systems and allow for data-sampling with fewer acquisitions than classical imaging techniques, even under the Nyquist rate. However, compressive hyperspectral imaging requires a reconstruction algorithm in order to recover all the data from the raw compressed acquisition. The reconstruction process is one of the limiting factors for the spread of these devices, as it is generally time-consuming and comes with a high computational burden. Algorithmic and material acceleration with embedded and parallel architectures (e.g., GPUs and FPGAs) can considerably speed up image reconstruction, making hyperspectral compressive systems suitable for real-time applications. This paper provides an in-depth analysis of the required performance in terms of computing power, data memory and bandwidth considering a compressive hyperspectral imaging system and a state-of-the-art reconstruction algorithm as an example. The results of the analysis show that real-time application is possible by combining several approaches, namely, exploitation of system matrix sparsity and bandwidth reduction by appropriately tuning data value encoding.

关键词： compressive sensing CGNE DD CASSI hyperspectral imaging computation complexity embedded systems remote sensing field-programmable gate array (FPGA) graphics processing unit (GPU)

来源：评论

学校读者我要写书评

暂无评论

Simulation-Optimization of Reservoir Water Quality under Climate Change

引用

JOURNAL OF WATER RESOURCES PLANNING AND MANAGEMENT 2021年第9期147卷 04021054-04021054页

作者： Azadi, Firoozeh Ashofteh, Parisa-Sadat Shokri, Ashkan Loaiciga, Hugo A. Univ Qom Dept Civil Engn Qom *** Iran Clayton Monash Univ Dept Civil Engn Melbourne Vic 3001 Australia Australian Bur Meteorol 700 Collins St Melbourne Vic 3001 Australia Univ Calif Santa Barbara Dept Geog Santa Barbara CA 93016 USA

Increasing population and water use, rising pollution of water resources, and climate change affect the quantity and quality of water resources. Reservoir operation is an important tool for water supply that can be optimized by simulation-optimization considering the impact of climate change on water quality. This study presents a simulation-optimization approach linking the CE-QUAL-W2 hydrodynamic model with the firefly algorithm k-nearest neighbor (FA-KNN) model to obtain optimal reservoir discharges to achieve water quality objectives under climate change conditions. The developed algorithm overcomes the computational burden of CE-QUAL-W2. The FA-KNN hybrid algorithm is employed to optimize the total dissolved solids (TDS) while achieving computational efficiently beyond what could be achieved with CE-QUAL-W2 simulations alone. This paper's approach is evaluated with the Aidoghmoush Reservoir (East Azerbaijan, Iran). Overall, 36 simulation-optimization scenarios for dry and wet years under baseline and climate change conditions are evaluated by considering three initial water levels for the reservoir (minimum, average, and normal) and three thresholds for assessing the hybrid algorithm. The TDS released from the reservoir in wet years would be acceptable for agricultural use;in dry years, on average, the TDS would not be acceptable for 24 days per year under climate change. The reservoir in winter undergoes complete mixing;it becomes stratified in spring and summer, and it is close to complete mixing in the autumn. The highest TDS in the reservoir would occur during the summer in dry years under climate change, reaching TDS of approximately 2,645 g/m(3). (C) 2021 American Society of Civil Engineers.

关键词： Water quality simulation-optimization CE-QUAL-W2 computation complexity Firefly algorithm k-nearest neighbor (FA-KNN) Climate change Reservoir water quality management

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：