The Experts below are selected from a list of 64983 Experts worldwide ranked by ideXlab platform

Jun Wang - One of the best experts on this subject based on the ideXlab platform.

  • The Prediction Model of Cotton Yarn Quality Based on Artificial Recurrent Neural Network
    International Conference on Applications and Techniques in Cyber Intelligence ATCI 2019, 2020
    Co-Authors: Zhenlong Hu, Qiang Zhao, Jun Wang
    Abstract:

    It is key index of cotton yarn quality such as cotton yarn strength and so on. It can well control cotton yarn quality by predicting yarn strength and so on. Generally, it is normal used to predict yarn strength such as Multiple Linear Regression (MLR), Support Vector Regression (SVR) and shallow Artificial Neural Network (ANN). Because the processing of cotton yarn production has time sequence, the paper proposes a new deep Neural Network, it is artificial Recurrent Neural Network (RNN). It used 1800 sets of data to train RNN, SVR and ANN. It tested RNN, MLR, SVR and ANN with 200 sets of data. Experimental results show that the Recurrent Neural Network (RNN) is the best accuracy among these four algorithms.

  • a one layer Recurrent Neural Network with a discontinuous hard limiting activation function for quadratic programming
    IEEE Transactions on Neural Networks, 2008
    Co-Authors: Jun Wang
    Abstract:

    In this paper, a one-layer Recurrent Neural Network with a discontinuous hard-limiting activation function is proposed for quadratic programming. This Neural Network is capable of solving a large class of quadratic programming problems. The state variables of the Neural Network are proven to be globally stable and the output variables are proven to be convergent to optimal solutions as long as the objective function is strictly convex on a set defined by the equality constraints. In addition, a sequential quadratic programming approach based on the proposed Recurrent Neural Network is developed for general nonlinear programming. Simulation results on numerical examples and support vector machine (SVM) learning show the effectiveness and performance of the Neural Network.

  • A one-layer Recurrent Neural Network for support vector machine learning.
    IEEE transactions on systems man and cybernetics. Part B Cybernetics : a publication of the IEEE Systems Man and Cybernetics Society, 2004
    Co-Authors: Youshen Xia, Jun Wang
    Abstract:

    This paper presents a one-layer Recurrent Neural Network for support vector machine (SVM) learning in pattern classification and regression. The SVM learning problem is first converted into an equivalent formulation, and then a one-layer Recurrent Neural Network for SVM learning is proposed. The proposed Neural Network is guaranteed to obtain the optimal solution of support vector classification and regression. Compared with the existing two-layer Neural Network for the SVM classification, the proposed Neural Network has a low complexity for implementation. Moreover, the proposed Neural Network can converge exponentially to the optimal solution of SVM learning. The rate of the exponential convergence can be made arbitrarily high by simply turning up a scaling parameter. Simulation examples based on benchmark problems are discussed to show the good performance of the proposed Neural Network for SVM learning.

  • a Recurrent Neural Network for solving sylvester equation with time varying coefficients
    IEEE Transactions on Neural Networks, 2002
    Co-Authors: Yunong Zhang, Danchi Jiang, Jun Wang
    Abstract:

    Presents a Recurrent Neural Network for solving the Sylvester equation with time-varying coefficient matrices. The Recurrent Neural Network with implicit dynamics is deliberately developed in the way that its trajectory is guaranteed to converge exponentially to the time-varying solution of a given Sylvester equation. Theoretical results of convergence and sensitivity analysis are presented to show the desirable properties of the Recurrent Neural Network. Simulation results of time-varying matrix inversion and online nonlinear output regulation via pole assignment for the ball and beam system and the inverted pendulum on a cart system are also included to demonstrate the effectiveness and performance of the proposed Neural Network.

  • a multilayer Recurrent Neural Network for solving continous time algebraic riccati equations
    Neural Networks, 1998
    Co-Authors: Jun Wang, Guang Wu
    Abstract:

    A multilayer Recurrent Neural Network is proposed for solving continuous-time algebraic matrix Riccati equations in real time. The proposed Recurrent Neural Network consists of four bidirectionally connected layers. Each layer consists of an array of neurons. The proposed Recurrent Neural Network is shown to be capable of solving algebraic Riccati equations and synthesizing linear-quadratic control systems in real time. Analytical results on stability of the Recurrent Neural Network and solvability of algebraic Riccati equations by use of the Recurrent Neural Network are discussed. The operating characteristics of the Recurrent Neural Network are also demonstrated through three illustrative examples.

Tomas Mikolov - One of the best experts on this subject based on the ideXlab platform.

  • Context Dependent Recurrent Neural Network Language Model
    IEEE Workshop on Spoken Language Technology (SLT), 2012
    Co-Authors: Tomas Mikolov, Geoffrey Zweig
    Abstract:

    Recurrent Neural Network language models (RNNLMs) have recently demonstrated state-of-the-art performance across a variety of tasks. In this paper, we improve their performance by providing a contextual real-valued input vector in association with each word. This vector is used to convey contextual information about the sentence being modeled. By performing Latent Dirichlet Allocation using a block of preceding text, we achieve a topic-conditioned RNNLM. This approach has the key advantage of avoiding the data fragmentation associated with building multiple topic models on different data subsets. We report perplexity results on the Penn Treebank data, where we achieve a new state-of-the-art.We further apply the model to the Wall Street Journal speech recognition task, where we observe improvements in word-error-rate.

  • Extensions of Recurrent Neural Network language model
    ICASSP IEEE International Conference on Acoustics Speech and Signal Processing - Proceedings, 2011
    Co-Authors: Tomas Mikolov, Jan Honza Černocký, Stefan Kombrink, Lukas Burget, Sanjeev Khudanpur
    Abstract:

    We present several modifications of the original Recurrent Neural Network language model (RNN LM).While this model has been shown to significantly outperform many competitive language modeling techniques in terms of accuracy, the remaining problem is the computational complexity. In this work, we show approaches that lead to more than 15 times speedup for both training and testing phases. Next, we show importance of using a backpropagation through time algorithm. An empirical comparison with feedforward Networks is also provided. In the end, we discuss possibilities how to reduce the amount of parameters in the model. The resulting RNN model can thus be smaller, faster both during training and testing, and more accurate than the basic one. © 2011 IEEE.

  • RNNLM --- Recurrent Neural Network Language Modeling Toolkit
    Proceedings of ASRU 2011, 2011
    Co-Authors: Tomas Mikolov, Anoop Deoras, Stefan Kombrink, Lukas Burget, Jan Honza Černocký
    Abstract:

    —We present freely available open-source toolkit for training Recurrent Neural Network based language models. It can be easily used to improve existing speech recognition and machine translation systems. Also, it can be used as a baseline for future research of advanced language modeling techniques. In the paper, we discuss optimal parameter selection and different modes of functionality. The toolkit, example scripts and basic setups are freely available at http://rnnlm.sourceforge.net/.

  • Recurrent Neural Network based language modeling in meeting recognition
    Proceedings of the Annual Conference of the International Speech Communication Association INTERSPEECH, 2011
    Co-Authors: Stefan Kombrink, Martin Karafiát, Tomas Mikolov, Lukas Burget
    Abstract:

    We use Recurrent Neural Network (RNN) based language mod- els to improve the BUT English meeting recognizer. On the baseline setup using the original language models we decrease word error rate (WER) more than 1% absolute by n-best list rescoring and language model adaptation. When n-gram lan- guage models are trained on the same moderately sized data set as the RNN models, improvements are higher yielding a system which performs comparable to the baseline. A noticeable im- provement was observed with unsupervised adaptation of RNN models. Furthermore, we examine the influence of word his- tory on WER and show how to speed-up rescoring by caching common prefix strings.

  • Recurrent Neural Network based language modeling in meeting recognition
    Conference of the International Speech Communication Association, 2011
    Co-Authors: Stefan Kombrink, Martin Karafiát, Tomas Mikolov, Lukas Burget
    Abstract:

    We use Recurrent Neural Network (RNN) based language models to improve the BUT English meeting recognizer. On the baseline setup using the original language models we decrease word error rate (WER) more than 1% absolute by n-best list rescoring and language model adaptation. When n-gram language models are trained on the same moderately sized data set as the RNN models, improvements are higher yielding a system which performs comparable to the baseline. A noticeable improvement was observed with unsupervised adaptation of RNN models. Furthermore, we examine the influence of word history on WER and show how to speed-up rescoring by caching common prefix strings. Index Terms: automatic speech recognition, language modeling, Recurrent Neural Networks, rescoring, adaptation

Lukas Burget - One of the best experts on this subject based on the ideXlab platform.

  • Extensions of Recurrent Neural Network language model
    ICASSP IEEE International Conference on Acoustics Speech and Signal Processing - Proceedings, 2011
    Co-Authors: Tomas Mikolov, Jan Honza Černocký, Stefan Kombrink, Lukas Burget, Sanjeev Khudanpur
    Abstract:

    We present several modifications of the original Recurrent Neural Network language model (RNN LM).While this model has been shown to significantly outperform many competitive language modeling techniques in terms of accuracy, the remaining problem is the computational complexity. In this work, we show approaches that lead to more than 15 times speedup for both training and testing phases. Next, we show importance of using a backpropagation through time algorithm. An empirical comparison with feedforward Networks is also provided. In the end, we discuss possibilities how to reduce the amount of parameters in the model. The resulting RNN model can thus be smaller, faster both during training and testing, and more accurate than the basic one. © 2011 IEEE.

  • RNNLM --- Recurrent Neural Network Language Modeling Toolkit
    Proceedings of ASRU 2011, 2011
    Co-Authors: Tomas Mikolov, Anoop Deoras, Stefan Kombrink, Lukas Burget, Jan Honza Černocký
    Abstract:

    —We present freely available open-source toolkit for training Recurrent Neural Network based language models. It can be easily used to improve existing speech recognition and machine translation systems. Also, it can be used as a baseline for future research of advanced language modeling techniques. In the paper, we discuss optimal parameter selection and different modes of functionality. The toolkit, example scripts and basic setups are freely available at http://rnnlm.sourceforge.net/.

  • Recurrent Neural Network based language modeling in meeting recognition
    Proceedings of the Annual Conference of the International Speech Communication Association INTERSPEECH, 2011
    Co-Authors: Stefan Kombrink, Martin Karafiát, Tomas Mikolov, Lukas Burget
    Abstract:

    We use Recurrent Neural Network (RNN) based language mod- els to improve the BUT English meeting recognizer. On the baseline setup using the original language models we decrease word error rate (WER) more than 1% absolute by n-best list rescoring and language model adaptation. When n-gram lan- guage models are trained on the same moderately sized data set as the RNN models, improvements are higher yielding a system which performs comparable to the baseline. A noticeable im- provement was observed with unsupervised adaptation of RNN models. Furthermore, we examine the influence of word his- tory on WER and show how to speed-up rescoring by caching common prefix strings.

  • Recurrent Neural Network based language modeling in meeting recognition
    Conference of the International Speech Communication Association, 2011
    Co-Authors: Stefan Kombrink, Martin Karafiát, Tomas Mikolov, Lukas Burget
    Abstract:

    We use Recurrent Neural Network (RNN) based language models to improve the BUT English meeting recognizer. On the baseline setup using the original language models we decrease word error rate (WER) more than 1% absolute by n-best list rescoring and language model adaptation. When n-gram language models are trained on the same moderately sized data set as the RNN models, improvements are higher yielding a system which performs comparable to the baseline. A noticeable improvement was observed with unsupervised adaptation of RNN models. Furthermore, we examine the influence of word history on WER and show how to speed-up rescoring by caching common prefix strings. Index Terms: automatic speech recognition, language modeling, Recurrent Neural Networks, rescoring, adaptation

  • Recurrent Neural Network based Language Model
    Interspeech, 2010
    Co-Authors: Tomas Mikolov, Jan Honza Černocký, Martin Karafiát, Lukas Burget, Sanjeev Khudanpur
    Abstract:

    A new Recurrent Neural Network based language model (RNN LM) with applications to speech recognition is presented. Re- sults indicate that it is possible to obtain around 50% reduction of perplexity by using mixture of several RNN LMs, compared to a state of the art backoff language model. Speech recognition experiments show around 18% reduction of word error rate on theWall Street Journal task when comparing models trained on the same amount of data, and around 5% on the much harder NIST RT05 task, even when the backoff model is trained on much more data than the RNN LM.We provide ample empiri- cal evidence to suggest that connectionist language models are superior to standard n-gram techniques, except their high com- putational (training) complexity.

Sanjeev Khudanpur - One of the best experts on this subject based on the ideXlab platform.

  • Extensions of Recurrent Neural Network language model
    ICASSP IEEE International Conference on Acoustics Speech and Signal Processing - Proceedings, 2011
    Co-Authors: Tomas Mikolov, Jan Honza Černocký, Stefan Kombrink, Lukas Burget, Sanjeev Khudanpur
    Abstract:

    We present several modifications of the original Recurrent Neural Network language model (RNN LM).While this model has been shown to significantly outperform many competitive language modeling techniques in terms of accuracy, the remaining problem is the computational complexity. In this work, we show approaches that lead to more than 15 times speedup for both training and testing phases. Next, we show importance of using a backpropagation through time algorithm. An empirical comparison with feedforward Networks is also provided. In the end, we discuss possibilities how to reduce the amount of parameters in the model. The resulting RNN model can thus be smaller, faster both during training and testing, and more accurate than the basic one. © 2011 IEEE.

  • Recurrent Neural Network based Language Model
    Interspeech, 2010
    Co-Authors: Tomas Mikolov, Jan Honza Černocký, Martin Karafiát, Lukas Burget, Sanjeev Khudanpur
    Abstract:

    A new Recurrent Neural Network based language model (RNN LM) with applications to speech recognition is presented. Re- sults indicate that it is possible to obtain around 50% reduction of perplexity by using mixture of several RNN LMs, compared to a state of the art backoff language model. Speech recognition experiments show around 18% reduction of word error rate on theWall Street Journal task when comparing models trained on the same amount of data, and around 5% on the much harder NIST RT05 task, even when the backoff model is trained on much more data than the RNN LM.We provide ample empiri- cal evidence to suggest that connectionist language models are superior to standard n-gram techniques, except their high com- putational (training) complexity.

  • Recurrent Neural Network based language model
    Conference of the International Speech Communication Association, 2010
    Co-Authors: Tomas Mikolov, Martin Karafiát, Lukas Burget, Jan Cernocký, Sanjeev Khudanpur
    Abstract:

    A new Recurrent Neural Network based language model (RNN LM) with applications to speech recognition is presented. Results indicate that it is possible to obtain around 50% reduction of perplexity by using mixture of several RNN LMs, compared to a state of the art backoff language model. Speech recognition experiments show around 18% reduction of word error rate on the Wall Street Journal task when comparing models trained on the same amount of data, and around 5% on the much harder NIST RT05 task, even when the backoff model is trained on much more data than the RNN LM. We provide ample empirical evidence to suggest that connectionist language models are superior to standard n-gram techniques, except their high computational (training) complexity. Index Terms: language modeling, Recurrent Neural Networks, speech recognition

Stefan Kombrink - One of the best experts on this subject based on the ideXlab platform.

  • Extensions of Recurrent Neural Network language model
    ICASSP IEEE International Conference on Acoustics Speech and Signal Processing - Proceedings, 2011
    Co-Authors: Tomas Mikolov, Jan Honza Černocký, Stefan Kombrink, Lukas Burget, Sanjeev Khudanpur
    Abstract:

    We present several modifications of the original Recurrent Neural Network language model (RNN LM).While this model has been shown to significantly outperform many competitive language modeling techniques in terms of accuracy, the remaining problem is the computational complexity. In this work, we show approaches that lead to more than 15 times speedup for both training and testing phases. Next, we show importance of using a backpropagation through time algorithm. An empirical comparison with feedforward Networks is also provided. In the end, we discuss possibilities how to reduce the amount of parameters in the model. The resulting RNN model can thus be smaller, faster both during training and testing, and more accurate than the basic one. © 2011 IEEE.

  • RNNLM --- Recurrent Neural Network Language Modeling Toolkit
    Proceedings of ASRU 2011, 2011
    Co-Authors: Tomas Mikolov, Anoop Deoras, Stefan Kombrink, Lukas Burget, Jan Honza Černocký
    Abstract:

    —We present freely available open-source toolkit for training Recurrent Neural Network based language models. It can be easily used to improve existing speech recognition and machine translation systems. Also, it can be used as a baseline for future research of advanced language modeling techniques. In the paper, we discuss optimal parameter selection and different modes of functionality. The toolkit, example scripts and basic setups are freely available at http://rnnlm.sourceforge.net/.

  • Recurrent Neural Network based language modeling in meeting recognition
    Proceedings of the Annual Conference of the International Speech Communication Association INTERSPEECH, 2011
    Co-Authors: Stefan Kombrink, Martin Karafiát, Tomas Mikolov, Lukas Burget
    Abstract:

    We use Recurrent Neural Network (RNN) based language mod- els to improve the BUT English meeting recognizer. On the baseline setup using the original language models we decrease word error rate (WER) more than 1% absolute by n-best list rescoring and language model adaptation. When n-gram lan- guage models are trained on the same moderately sized data set as the RNN models, improvements are higher yielding a system which performs comparable to the baseline. A noticeable im- provement was observed with unsupervised adaptation of RNN models. Furthermore, we examine the influence of word his- tory on WER and show how to speed-up rescoring by caching common prefix strings.

  • Recurrent Neural Network based language modeling in meeting recognition
    Conference of the International Speech Communication Association, 2011
    Co-Authors: Stefan Kombrink, Martin Karafiát, Tomas Mikolov, Lukas Burget
    Abstract:

    We use Recurrent Neural Network (RNN) based language models to improve the BUT English meeting recognizer. On the baseline setup using the original language models we decrease word error rate (WER) more than 1% absolute by n-best list rescoring and language model adaptation. When n-gram language models are trained on the same moderately sized data set as the RNN models, improvements are higher yielding a system which performs comparable to the baseline. A noticeable improvement was observed with unsupervised adaptation of RNN models. Furthermore, we examine the influence of word history on WER and show how to speed-up rescoring by caching common prefix strings. Index Terms: automatic speech recognition, language modeling, Recurrent Neural Networks, rescoring, adaptation