检索结果-内蒙古大学图书馆

GENERAL METHOD FOR training COMMITTEE MACHINE

PATTERN RECOGNITION 1978年第4期10卷 255-259页

作者： TAKIYAMA, R Department of Visual Communication Design Kyushu Institute of Design Fukuoka 815 Japan

A method for training the committee machine with an arbitrary logic is described. First, an expression of the discriminant function realized by the committee machine is introduced. By making use of the expression, an error-correction procedure for training the committee machine is proposed. The procedure of the perceptron is clearly explained as the special case of the proposed procedure. Experimental results show that the procedure is effective.

关键词： Perceptron Pattern classification Committee machine training algorithm Discriminant function

来源：评论

学校读者我要写书评

暂无评论

BOOKS ON TAPE AS training DATA FOR CONTINUOUS SPEECH RECOGNITION

引用

SPEECH COMMUNICATION 1994年第1期14卷 61-70页

作者： BOULIANNE, G KENNY, P LENNIG, M OSHAUGHNESSY, D MERMELSTEIN, P BELL NO RES LTD MONTREAL PQ CANADA

training algorithms for natural speech recognition require very large amounts of transcribed speech data. Commercially distributed books on tape constitute an abundant source of such data, but it is difficult to take advantage of it using current training algorithms because of the requirement that the data be hand-segmented into chunks that can be comfortably processed in memory. In order to address this problem we have developed a training algorithm which is capable of handling unsegmented data files of arbitrary length;the computational requirements of the algorithm are linear in the amount of data to be processed and the memory requirements are constant.

关键词： HIDDEN MARKOV MODEL CONTINUOUS SPEECH RECOGNITION training algorithm SPEECH SEGMENTATION SPEECH LABELING VITERBI DECODING

来源：评论

学校读者我要写书评

暂无评论

A Simple training Strategy for Graph Autoencoder 2020

A Simple Training Strategy for Graph Autoencoder

引用

12th International Conference on Machine Learning and Computing (ICMLC)

作者： Wang, Yingfeng Xu, Biyun Kwak, Myungjae Zeng, Xiaoqin Middle Georgia State Univ 100 Univ Pkwy Macon GA 31206 USA Beijing Kubao Technol Co 1089 Huihe South St Beijing Peoples R China Hohai Univ 1 Xikang Rd Nanjing Jiangsu Peoples R China

ISBN: (纸本)9781450376426

Graph autoencoder can map graph data into a low-dimensional space. It is a powerful graph embedding method applied in graph analytics to reduce the computational cost. The training algorithm of a graph autoencoder searches the weight setting for preserving most graph information of the graph data with reduced dimensionality. This paper presents a simple training strategy, which can improve the training performance without significantly increasing time complexity. This strategy can flexibly fit many existing training algorithms. The experimental results confirm the effectiveness of this strategy.

关键词： Autoencoder Graph Convolutional Network Perturbation training algorithm

来源：评论

学校读者我要写书评

暂无评论

Momentum Acceleration of Quasi-Newton training for Neural Networks 16th

Momentum Acceleration of Quasi-Newton Training for Neural Ne...

引用

16th Pacific Rim International Conference on Artificial Intelligence (PRICAI)

作者： Mahboubi, Shahrzad Indrapriyadarsini, S. Ninomiya, Hiroshi Asai, Hideki Shonan Inst Technol 1-1-25 Tsujido Nishikaigan Fujisawa Kanagawa 2518511 Japan Shizuoka Univ Naka Ku 3-5-1 Johoku Hamamatsu Shizuoka 4328011 Japan

ISBN: (纸本)9783030299118;9783030299101

This paper describes a novel acceleration technique of quasi-Newton method (QN) using momentum terms for training in neural networks. Recently, Nesterov's accelerated quasi-Newton method (NAQ) has shown that the momentum term is effective in reducing the number of iterations and in accelerating its convergence speed. However, the gradients had to calculate two times during one iteration in the NAQ training. This increased the computation time of a training loop compared with the conventional QN. In this research, an improvement to NAQ is done by approximating the Nesterov's accelerated gradient used in NAQ as a linear combination of the current and previous gradients. Then the gradient is calculated only once per iteration same as QN. The performance of the proposed algorithm is evaluated through computer simulations on a benchmark problem of the function modeling and real-world problems of the microwave circuit modeling. The results show the significant acceleration in the computation time compared with conventional training algorithms.

关键词： Neural networks training algorithm Quasi-Newton method Nesterov's accelerated quasi-Newton method Momentum terms

来源：评论

学校读者我要写书评

暂无评论

training Method for a Feed Forward Neural Network Based on Meta-heuristics 13th

Training Method for a Feed Forward Neural Network Based on M...

引用

13th International Conference on Intelligent Information Hiding and Multimedia Signal Processing (IIH-MSP)

作者： Melo, Haydee Zhang, Huiming Vasant, Pandian Watada, Junzo Waseda Univ Grad Sch Prod Informat & Syst Tokyo Japan Univ Teknol PETRONAS Fundamental & Appl Sci Dept Seri Iskandar Malaysia Univ Teknol PETRONAS Deparment Comp & Informat Sci Seri Iskandar Malaysia

ISBN: (纸本)9783319638591;9783319638584

This paper proposes a Gaussian-Cauchy Particle Swarm Optimization (PSO) algorithm to provide the optimized parameters for a Feed Forward Neural Network. The improved PSO trains the Neural Network by optimizing the network weights and bias in the Neural Network. In comparison with the Back Propagation Neural Network, the Gaussian-Cauchy PSO Neural Network converges faster and is immune to local minima.

关键词： Particle Swarm Optimization Neural network training algorithm Gaussian distribution Cauchy distribution

来源：评论

学校读者我要写书评

暂无评论

Memristor Crossbar Based Unsupervised training

Memristor Crossbar Based Unsupervised Training

引用

IEEE National Aerospace and Electronics Conference (NAECON)

作者： Hasan, Raqibul Taha, Tarek M. Univ Dayton Dept Elect & Comp Engn Dayton OH 45469 USA

ISBN: (纸本)9781467375658

Several big data applications are particularly focused on classification and clustering tasks. Robustness of such system depends on how well it can extract important features from the raw data. For big data processing we are interested for a generic feature extraction mechanism for different applications. autoencoder is a popular unsupervised training algorithm for dimensionality reduction and feature extraction. In this work we have examined memiistor crossbar based implementation of autoencoder which will consume very low power. We have designed on-chip training circuitry for the unsupervised training scheme.

关键词： Low power architecture memristor crossbars autoencoder training algorithm feature extraction

来源：评论

学校读者我要写书评

暂无评论

Neural Network training based on quasi-Newton Method using Nesterov's Accelerated Gradient

Neural Network Training based on quasi-Newton Method using N...

引用

IEEE Region 10 Conference (TENCON)

作者： Ninomiya, Hiroshi Shonan Inst Technol Dept Informat Sci 1-1-25 Tsujido Nishikaigan Fujisawa Kanagawa 2518511 Japan

ISBN: (纸本)9781509025978

This paper describes a novel quasi-Newton (QN) based accelerated technique for training of neural networks. Recently, Nesterov's accelerated gradient method has been utilized for training the neural networks. In this paper the acceleration of the QN training algorithm is realized using Momentum term in Nesterov's method. It is shown that the proposed algorithm has a similar convergence property with the conventional QN method. Neural network training for a simple function approximation and a microwave circuit modeling is presented to demonstrate the proposed algorithm. The proposed algorithm drastically improves the convergence speed of the QN algorithm.

关键词： neural networks training algorithm Nesterov's accelerated gradient method quasi-Newton method

来源：评论

学校读者我要写书评

暂无评论

training Deep Neural Networks with Constrained Learning Parameters

Training Deep Neural Networks with Constrained Learning Para...

引用

IEEE International Conference on Rebooting Computing (ICRC)

作者： Date, Prasanna Carothers, Christopher D. Mitchell, John E. Hendler, James A. Magdon-Ismail, Malik Rensselaer Polytech Inst Dept Comp Sci Troy NY 12180 USA Rensselaer Polytech Inst Dept Math Sci Troy NY 12180 USA

ISBN: (纸本)9780738143378

Today's deep learning models are primarily trained on CPUs and GPUs. Although these models tend to have low error, they consume high power and utilize large amount of memory owing to double precision floating point learning parameters. Beyond the Moore's law, a significant portion of deep learning tasks would run on edge computing systems, which will form an indispensable part of the entire computation fabric. Subsequently, training deep learning models for such systems will have to be tailored and adopted to generate models that have the following desirable characteristics: low error, low memory, and low power. We believe that deep neural networks (DNNs), where learning parameters are constrained to have a set of finite discrete values, running on neuromorphic computing systems would be instrumental for intelligent edge computing systems having these desirable characteristics. To this extent, we propose the Combinatorial Neural Network training algorithm (CoNNTrA), that leverages a coordinate gradient descent-based approach for training deep learning models with finite discrete learning parameters. Next, we elaborate on the theoretical underpinnings and evaluate the computational complexity of CoNNTrA. As a proof of concept, we use CoNNTrA to train deep learning models with ternary learning parameters on the MNIST, Iris and ImageNet data sets and compare their performance to the same models trained using Backpropagation. We use following performance metrics for the comparison: (i) training error;(ii) Validation error;(iii) Memory usage;and (iv) training time. Our results indicate that CoNNTrA models use 32x less memory and have errors at par with the Backpropagation models.

关键词： Deep Neural Networks training algorithm Deep Learning Machine Learning Artificial Intelligence

来源：评论

学校读者我要写书评

暂无评论

On-chip training of Memristor Based Deep Neural Networks

On-chip Training of Memristor Based Deep Neural Networks

引用

International Joint Conference on Neural Networks (IJCNN)

作者： Hasan, Raqibul Taha, Tarek M. Yakopcic, Chris Univ Dayton Dept Elect & Comp Engn Dayton OH 45469 USA

ISBN: (纸本)9781509061822

This paper presents on-chip training circuits for memristor based deep neural networks utilizing unsupervised and supervised learning methods. Memristor crossbar circuits allow neural algorithms to be implemented very efficiently, but could be prone to device variations and faults. On chip training circuits would allow the training algorithm to account for device variability and faults in these circuits. We have utilized autoencoders for layer-wise pre-training of the deep networks and utilized the back-propagation algorithm for supervised fine tuning. Our design utilizes two memristors per synapse for higher precision of weights. We have demonstrated successful training of memristor based deep networks for the MNIST digit classification and the KDD intrusion detection datasets.

关键词： Deep networks memristor crossbars training algorithm on-chip training circuit

来源：评论

学校读者我要写书评

暂无评论

Manhattan Rule training for Memristive Crossbar Circuit Pattern Classifiers 9

Manhattan Rule Training for Memristive Crossbar Circuit Patt...

引用

IEEE 9th International Symposium on Intelligent Signal Processing (WISP)

作者： Zamanidoost, Elham Bayat, Farnood M. Strukov, Dmitri Kataeva, Irina Univ Calif Santa Barbara Dept Elect & Comp Engn Santa Barbara CA 93106 USA Denso Corp Adv Res Div Komenoki Nisshin Japan

ISBN: (纸本)9781479972524

We investigated batch and stochastic Manhattan Rule algorithms for training multilayer perceptron classifiers implemented with memristive crossbar circuits. In Manhattan Rule training, the weights are updated only using sign information of classical backpropagation algorithm. The main advantage of Manhattan Rule is its simplicity, which leads to more compact hardware implementation and faster training time. Additionally, in case of stochastic training, Manhattan Rule allows performing all weight updates in parallel, which further speeds up the training procedure. The tradeoff for simplicity is slightly worse classification performance. For example, simulation results showed that classification fidelity on Proben1 benchmark for memristor-based implementation trained with batch Manhattan Rule were comparable to that of classical backpropagation algorithm, and about 2.8 percent worse than the best reported results.

关键词： Crossbar memory Memristor Artificial neural network training algorithm Pattern classification

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：