检索结果-内蒙古大学图书馆

7th International Conference of the Experience of Designing and Application of CAD Systems in Microelectronics

作者： Mykhalchan, V

来源：评论

学校读者我要写书评

暂无评论

Modifications of the Givens training algorithm for Artificial Neural Networks 18th

Modifications of the Givens Training Algorithm for Artificia...

引用

18th International Conference on Artificial Intelligence and Soft Computing (ICAISC)

作者： Bilski, Jaroslaw Kowalczyk, Bartosz Cader, Andrzej Czestochowa Tech Univ Inst Computat Intelligence Czestochowa Poland Univ Social Sci Informat Technol Inst Lodz Poland Clark Univ Worcester MA 01610 USA

ISBN: (纸本)9783030209124;9783030209117

The Givens algorithm is a supervised training method for neural networks. This paper presents several optimization techniques that could be applied on the top of the Givens algorithm. First, the classic variant of the Givens method is briefly described. The main section of the article contains a detailed description of the proposed retry worst samples, skip best samples, and the Givens epoch update optimization techniques. The paper concludes with the simulation results and an overall summary.

关键词： Feed-forward neural network training algorithm Optimization QR decomposition Givens rotation training acceleration

来源：评论

学校读者我要写书评

暂无评论

The Improved training algorithm of Back Propagation Neural Network with Self-adaptive Learning Rate

The Improved Training Algorithm of Back Propagation Neural N...

引用

International Conference on Computational Intelligence and Natural Computing

作者： Li, Yong Fu, Yang Li, Hui Zhang, Si-Wen NE Dianli Univ Sch Energy Resources & Mech Engn Jilin Peoples R China

ISBN: (纸本)9780769536453

This paper addresses the questions of improving convergence performance for back propagation (BP) neural network. For traditional BP neural network algorithm, the learning rate selection is depended on experience and trial. In this paper, based on Taylor formula the function relationship between the total quadratic training error change and connection weights and biases changes is obtained, and combined with weights and biases changes in batch BP learning algorithm, the formula for self-adaptive learning rate is given. Unlike existing algorithm, the self-adaptive learning rate depends on only neural network topology, training samples, average quadratic error and error curve surface gradient but not artificial selection. Simulation results show iteration times is significant less than that of traditional batch BP learning algorithm with constant learning rate.

关键词： artificial neural network back propagation neural network training algorithm learning rate self-adaptive

来源：评论

学校读者我要写书评

暂无评论

Improved SMPS Modeling for Photovoltaic Applications by a Novel Neural Paradigm with Hamiltonian-Based training algorithm 5

Improved SMPS Modeling for Photovoltaic Applications by a No...

引用

5th International Conference on Clean Electrical Power (ICCEP)

作者： Bonanno, F. Capizzi, G. Lo Sciuto, G. Univ Catania Dept Elect Elect & Informat Engn I-95124 Catania Italy Univ Rome Tre Dept Engn I-00146 Rome Italy

ISBN: (纸本)9781479987047

This paper discuss as the dynamics of a SMPS can be investigated by recurrent neural network (RNN) based models with an Hamiltonian formulation and function used for the training, so leading to a novel paradigm that we call RNNHT model. By using the calculated state variables in a boost converter a RNN is trained by considering also the minimization of the energy stored according to a defined cost function. Simulation results show the improvements in the dynamic performance output prediction versus some well assessed boost converter models in the recent literature.

关键词： SMPS Boost converter Photovoltaic Dynamic modeling Recurrent neural network Hamiltonian formulation training algorithm Simulation

来源：评论

学校读者我要写书评

暂无评论

A Framework for Selection of training algorithm of Neuro-Statistic Model for Prediction of Pig Breeds in India

引用

VIETNAM JOURNAL OF COMPUTER SCIENCE 2021年第1期8卷 153-175页

作者： Mandal, Satyendra Nath Ghosh, Pritam Shit, Nanigopal Hajra, Dilip Kumar Banik, Santanu Kalyani Govt Engn Coll Dept Informat Technol Nadia 741235 W Bengal India Uttar Banga Krishi Viswavidyalaya Dept Agron Cooch Behar 736165 W Bengal India ICAR Natl Res Ctr Pig Gauhati 781131 Assam India

Various training algorithms are used in artificial neural networks for updating the weights during training the network. But, the selection of the appropriate training algorithm is dependent on the input-output mapping of dataset for which the network is constructed. In this paper, a framework has been proposed consisting of five modules to select the optimal training algorithm for predicting pig breeds from their images. The individual pig images from five pig-breeds have been captured using inbuilt camera of mobile phone and the contour of pig has been segmented from each captured image by HUE-based segmentation algorithm. In Statistical Parameter and Color Component retrieval module, parameters like entropy, standard deviation, variance, mean, median, and mode and color properties like hue, saturation, value (HSV) extracted from the content of each segmented image. Values of all extracted parameters have been transferred into training algorithm Selection Module. In this module, a fitting neural network with different numbers of hidden neurons has been executed by feeding all extracted values from pig images for mapping their breeds. Ten training algorithms have been applied on the same extracted dataset separately for five epochs each keeping other network parameters constants. The mean square error (MSE) and correlation coefficient (R) for the validation set have been calculated after adjustment of weights and biases in each connection of the neurons. One training algorithm among 10 and its suitable number of hidden neurons has been selected based on comparative analysis for getting lower MSE and higher R in the validation set. Then, the fitting network with selected training algorithm has been run on the same extracted datasets until the stopping condition is reached. Then the test set images are fed into the network and the network output has been categorized to class which has been assigned to each breed of pig in Breed Prediction Module. The proposed framewo

关键词： Artificial neural network training algorithm image database segmentation statistical components color components

来源：评论

学校读者我要写书评

暂无评论

Stock Market Prediction Using an Improved training algorithm of Neural Network 2

Stock Market Prediction Using an Improved Training Algorithm...

引用

2nd International Conference on Electrical, Computer & Telecommunication Engineering (ICECTE)

作者： Billah, Mustain Waheed, Sajjad Hanifa, Abu Mawlana Bhashani Sci & Technol Univ Dept Informat & Commun Technol Tangail Bangladesh

ISBN: (纸本)9781509057856

Predicting closing stock price accurately is an challenging task. Computer aided systems have been proved to be helpful tool for stock prediction such as Artificial Neural Network( ANN), Adaptive Neuro Fuzzy Inference System (ANFIS) etc. Latest research works prove that Adaptive Neuro Fuzzy Inference System shows better results than Neural Network for stock prediction. In this paper, an improved Levenberg Marquardt(LM) training algorithm of artificial neural network has been proposed. Improved Levenberg Marquardt algorithm of neural network can predict the possible day-end closing stock price with less memory and time needed, provided previous historical stock market data of Dhaka Stock Exchange such as opening price, highest price, lowest price, total share traded. Morever, improved LM algorithm can predict day-end stock price with 53% less error than ANFIS and traditional LM algorithm. It also requires 30% less time, 54% less memory than traditional LM and 47% less time, 59% less memory than ANFIS.

关键词： Stock prediction Neural Netwok training algorithm Levenberg Marquardt Dhaka Stock Exchange

来源：评论

学校读者我要写书评

暂无评论

Adaptive Equalizer training algorithm to Correct for Frequency Dispersion in Transionospheric Radio Channels

Adaptive Equalizer Training Algorithm to Correct for Frequen...

引用

Wave Electronics and its Application in Information and Telecommunication Systems (WECONF)

作者： Ivanov, V. A. Kislitsin, A. A. Ivanov, D., V Chernov, A. A. Ovchinnikov, V. V. Volga State Univ Technol Yoshkar Ola Russia

ISBN: (纸本)9781728122885

We have developed a training algorithm for device that implements the method of frequency dispersion correction supported by the full-scale measurements in the transionospheric radio communication channels. It uses GNSS/GPS satellite systems data to compute total electron content of the ionosphere that impacts the behavior of frequency dispersion of signal delay. Periodic data update during the training allows to mitigate dispersion distortions in wideband transionospheric communication channels.

关键词： dispersion correction training algorithm transionospheric radio channel frequency dispersion total electron content channel lifetime

来源：评论

学校读者我要写书评

暂无评论

An Enhanced Swarm Intelligence based training algorithm for RBF Neural Networks in Function Approximation 2

An Enhanced Swarm Intelligence based Training Algorithm for ...

引用

2014 Second World Conference on Complex Systems (WCCS)

作者： Salem, Mohammed Zingla, Meriem Amina Khelfi, Mohamed Faycal Univ Mascara Fac Sci & Technol Mascara Algeria Univ Carthage LISI Res Lab INSAT Tunis Tunisia Univ Fac Appl & Exact Sci Oran Algeria

ISBN: (纸本)9781479946471

This paper is dedicated to the presentation of enhanced swarm intelligence based training algorithm for Radial basis functions neural networks. The proposed training algorithm (ABC-PP) is hybridization between the Artificial Bees Colony (ABC) and a predator and prey behavior to improve the diversification mechanism of the ABC. Statistical analysis is carried out with nonparametric tests to evaluate the proposed training algorithm comparing it with ABC, GA and PSO based RBF training algorithms in function approximation. The proposed algorithm is applied to identify a real inverted pendulum model giving acceptable results.

关键词： component Artificial Bees Colony predator and prey RBF neural networks training algorithm Nonparametric tests Function approximation Inverted pendulum

来源：评论

学校读者我要写书评

暂无评论

Modulation spectrum-constrained trajectory training algorithm for GMM-based Voice Conversion 40

Modulation spectrum-constrained trajectory training algorith...

引用

40th IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2015

作者： Takamichi, Shinnosuke Toda, Tomoki Black, Alan W. Nakamura, Satoshi Japan United States

ISBN: (纸本)9781467369978

This paper presents a novel training algorithm for Gaussian Mixture Model (GMM)-based Voice Conversion (VC). One of the advantages of GMM-based VC is computationally efficient conversion processing enabling to achieve real-time VC applications. On the other hand, the quality of the converted speech is still significantly worse than that of natural speech. In order to address this problem while preserving the computationally efficient conversion processing, the proposed training method enables 1) to use a consistent optimization criterion between training and conversion and 2) to compensate a Modulation Spectrum (MS) of the converted parameter trajectory as a feature sensitively correlated with over-smoothing effects causing quality degradation of the converted speech. The experimental results demonstrate that the proposed algorithm yields significant improvements in term of both the converted speech quality and the conversion accuracy for speaker individuality compared to the basic training algorithm. © 2015 IEEE.

关键词： GMM-based voice conversion modulation spectrum over-smoothing training algorithm

来源：评论

学校读者我要写书评

暂无评论

training algorithm to deceive Anti-Spoofing Verification for DNN-based speech synthesis

Training algorithm to deceive Anti-Spoofing Verification for...

引用

IEEE International Conference on Acoustics, Speech and Signal Processing

作者： Yuki Saito Shinnosuke Takamichi Hiroshi Saruwatari Graduate School of Information Science and Technology The University of Tokyo 7-3-1 Hongo Bunkyo-ku 113-8656 Japan

ISBN: (纸本)9781509041183

This paper proposes a novel training algorithm for high-quality Deep Neural Network (DNN)-based speech synthesis. The parameters of synthetic speech tend to be over-smoothed, and this causes significant quality degradation in synthetic speech. The proposed algorithm takes into account an Anti-Spoofing Verification (ASV) as an additional constraint in the acoustic model training. The ASV is a discriminator trained to distinguish natural and synthetic speech. Since acoustic models for speech synthesis are trained so that the ASV recognizes the synthetic speech parameters as natural speech, the synthetic speech parameters are distributed in the same manner as natural speech parameters. Additionally, we find that the algorithm compensates not only the parameter distributions, but also the global variance and the correlations of synthetic speech parameters. The experimental results demonstrate that 1) the algorithm outperforms the conventional training algorithm in terms of speech quality, and 2) it is robust against the hyper-parameter settings.

关键词： DNN-based speech synthesis anti-spoofing verification training algorithm generative adversarial training multitask learning Speech synthesis Speech VOCAL PARAMETERS adaptive supply voltage Acoustic models SYNTHETICS Functional training redundant constraint algorithms

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：