The Experts below are selected from a list of 83475 Experts worldwide ranked by ideXlab platform
Guang-bin Huang - One of the best experts on this subject based on the ideXlab platform.
-
Composite Function Wavelet Neural Networks with Differential Evolution and Extreme Learning Machine
Neural Processing Letters, 2011Co-Authors: Jiuwen Cao, Zhiping Lin, Guang-bin HuangAbstract:In this paper, we introduce a new learning method for Composite Function wavelet neural networks (CFWNN) by combining the differential evolution (DE) algorithm with extreme learning machine (ELM), in short, as CWN-E-ELM. The recently proposed CFWNN trained with ELM (CFWNN-ELM) has several promising features. But the CFWNN-ELM may have some redundant nodes due to the number of hidden nodes assigned a priori and the input weight matrix and the hidden node parameter vector randomly generated once and never changed during the learning phase. The introduction of DE into CFWNN-ELM is to search for the optimal network parameters and to reduce the number of hidden nodes used in the network. Simulations on several artificial Function approximations, real-world data regressions and a chaotic signal prediction problem show some advantages of the proposed CWN-E-ELM. Compared with CFWNN-ELM, CWN-E-ELM has a much more compact network size and Compared with several relevant methods, CWN-E-ELM is able to achieve a better generalization performance.
-
Composite Function wavelet neural networks with extreme learning machine
Neurocomputing, 2009Co-Authors: Jiuwen Cao, Zhiping Lin, Guang-bin HuangAbstract:A new structure of wavelet neural networks (WNN) with extreme learning machine (ELM) is introduced in this paper. In the proposed wavelet neural networks, Composite Functions are applied at the hidden nodes and the learning is done using ELM. The input information is first processed by wavelet Functions and then passed through a type of bounded nonconstant piecewise continuous activation Functions g:R->R. A selection method that takes into account the domain of input space where the wavelets are not zero is used to initialize the translation and dilation parameters. The formed wavelet neural network is then trained with the computationally efficient ELM algorithm. Experimental results on the regression of some nonlinear Functions and real-world data, the prediction of a chaotic signal and classifications on serval benchmark real-world data sets show that the proposed neural networks can achieve better performances in most cases than some relevant neural networks and learn much faster than neural networks training with the traditional back-propagation (BP) algorithm.
Jiehong R Jiang - One of the best experts on this subject based on the ideXlab platform.
-
quantifier elimination via Functional composition
Computer Aided Verification, 2009Co-Authors: Jiehong R JiangAbstract:This paper poses the following basic question: Given a quantified Boolean formula *** x . φ , what should a Function/formula f be such that substituting f for x in φ yields a logically equivalent quantifier-free formula? Its answer leads to a solution to quantifier elimination in the Boolean domain, alternative to the conventional approach based on formula expansion. Such a Composite Function can be effectively derived using symbolic techniques and further simplified for practical applications. In particular, we explore Craig interpolation for scalable computation. This compositional approach to quantifier elimination is analyzably superior to the conventional one under certain practical assumptions. Experiments demonstrate the scalability of the approach. Several large problem instances unsolvable before can now be resolved effectively. A generalization to first-order logic characterizes a Composite Function's complete flexibility, which awaits further exploitation to simplify quantifier elimination beyond the propositional case.
-
CAV - Quantifier Elimination via Functional Composition
Computer Aided Verification, 2009Co-Authors: Jiehong R JiangAbstract:This paper poses the following basic question: Given a quantified Boolean formula *** x . φ , what should a Function/formula f be such that substituting f for x in φ yields a logically equivalent quantifier-free formula? Its answer leads to a solution to quantifier elimination in the Boolean domain, alternative to the conventional approach based on formula expansion. Such a Composite Function can be effectively derived using symbolic techniques and further simplified for practical applications. In particular, we explore Craig interpolation for scalable computation. This compositional approach to quantifier elimination is analyzably superior to the conventional one under certain practical assumptions. Experiments demonstrate the scalability of the approach. Several large problem instances unsolvable before can now be resolved effectively. A generalization to first-order logic characterizes a Composite Function's complete flexibility, which awaits further exploitation to simplify quantifier elimination beyond the propositional case.
Jiuwen Cao - One of the best experts on this subject based on the ideXlab platform.
-
Composite Function Wavelet Neural Networks with Differential Evolution and Extreme Learning Machine
Neural Processing Letters, 2011Co-Authors: Jiuwen Cao, Zhiping Lin, Guang-bin HuangAbstract:In this paper, we introduce a new learning method for Composite Function wavelet neural networks (CFWNN) by combining the differential evolution (DE) algorithm with extreme learning machine (ELM), in short, as CWN-E-ELM. The recently proposed CFWNN trained with ELM (CFWNN-ELM) has several promising features. But the CFWNN-ELM may have some redundant nodes due to the number of hidden nodes assigned a priori and the input weight matrix and the hidden node parameter vector randomly generated once and never changed during the learning phase. The introduction of DE into CFWNN-ELM is to search for the optimal network parameters and to reduce the number of hidden nodes used in the network. Simulations on several artificial Function approximations, real-world data regressions and a chaotic signal prediction problem show some advantages of the proposed CWN-E-ELM. Compared with CFWNN-ELM, CWN-E-ELM has a much more compact network size and Compared with several relevant methods, CWN-E-ELM is able to achieve a better generalization performance.
-
Composite Function wavelet neural networks with extreme learning machine
Neurocomputing, 2009Co-Authors: Jiuwen Cao, Zhiping Lin, Guang-bin HuangAbstract:A new structure of wavelet neural networks (WNN) with extreme learning machine (ELM) is introduced in this paper. In the proposed wavelet neural networks, Composite Functions are applied at the hidden nodes and the learning is done using ELM. The input information is first processed by wavelet Functions and then passed through a type of bounded nonconstant piecewise continuous activation Functions g:R->R. A selection method that takes into account the domain of input space where the wavelets are not zero is used to initialize the translation and dilation parameters. The formed wavelet neural network is then trained with the computationally efficient ELM algorithm. Experimental results on the regression of some nonlinear Functions and real-world data, the prediction of a chaotic signal and classifications on serval benchmark real-world data sets show that the proposed neural networks can achieve better performances in most cases than some relevant neural networks and learn much faster than neural networks training with the traditional back-propagation (BP) algorithm.
Zhiping Lin - One of the best experts on this subject based on the ideXlab platform.
-
Composite Function Wavelet Neural Networks with Differential Evolution and Extreme Learning Machine
Neural Processing Letters, 2011Co-Authors: Jiuwen Cao, Zhiping Lin, Guang-bin HuangAbstract:In this paper, we introduce a new learning method for Composite Function wavelet neural networks (CFWNN) by combining the differential evolution (DE) algorithm with extreme learning machine (ELM), in short, as CWN-E-ELM. The recently proposed CFWNN trained with ELM (CFWNN-ELM) has several promising features. But the CFWNN-ELM may have some redundant nodes due to the number of hidden nodes assigned a priori and the input weight matrix and the hidden node parameter vector randomly generated once and never changed during the learning phase. The introduction of DE into CFWNN-ELM is to search for the optimal network parameters and to reduce the number of hidden nodes used in the network. Simulations on several artificial Function approximations, real-world data regressions and a chaotic signal prediction problem show some advantages of the proposed CWN-E-ELM. Compared with CFWNN-ELM, CWN-E-ELM has a much more compact network size and Compared with several relevant methods, CWN-E-ELM is able to achieve a better generalization performance.
-
Composite Function wavelet neural networks with extreme learning machine
Neurocomputing, 2009Co-Authors: Jiuwen Cao, Zhiping Lin, Guang-bin HuangAbstract:A new structure of wavelet neural networks (WNN) with extreme learning machine (ELM) is introduced in this paper. In the proposed wavelet neural networks, Composite Functions are applied at the hidden nodes and the learning is done using ELM. The input information is first processed by wavelet Functions and then passed through a type of bounded nonconstant piecewise continuous activation Functions g:R->R. A selection method that takes into account the domain of input space where the wavelets are not zero is used to initialize the translation and dilation parameters. The formed wavelet neural network is then trained with the computationally efficient ELM algorithm. Experimental results on the regression of some nonlinear Functions and real-world data, the prediction of a chaotic signal and classifications on serval benchmark real-world data sets show that the proposed neural networks can achieve better performances in most cases than some relevant neural networks and learn much faster than neural networks training with the traditional back-propagation (BP) algorithm.
Bernard Ghanem - One of the best experts on this subject based on the ideXlab platform.
-
CVPR - A Matrix Splitting Method for Composite Function Minimization
2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2017Co-Authors: Ganzhao Yuan, Wei-shi Zheng, Bernard GhanemAbstract:Composite Function minimization captures a wide spectrum of applications in both computer vision and machine learning. It includes bound constrained optimization and cardinality regularized optimization as special cases. This paper proposes and analyzes a new Matrix Splitting Method (MSM) for minimizing Composite Functions. It can be viewed as a generalization of the classical Gauss-Seidel method and the Successive Over-Relaxation method for solving linear systems in the literature. Incorporating a new Gaussian elimination procedure, the matrix splitting method achieves state-of-the-art performance. For convex problems, we establish the global convergence, convergence rate, and iteration complexity of MSM, while for non-convex problems, we prove its global convergence. Finally, we validate the performance of our matrix splitting method on two particular applications: nonnegative matrix factorization and cardinality regularized sparse coding. Extensive experiments show that our method outperforms existing Composite Function minimization techniques in term of both efficiency and efficacy.
-
A Matrix Splitting Method for Composite Function Minimization
arXiv: Optimization and Control, 2016Co-Authors: Ganzhao Yuan, Wei-shi Zheng, Bernard GhanemAbstract:Composite Function minimization captures a wide spectrum of applications in both computer vision and machine learning. It includes bound constrained optimization and cardinality regularized optimization as special cases. This paper proposes and analyzes a new Matrix Splitting Method (MSM) for minimizing Composite Functions. It can be viewed as a generalization of the classical Gauss-Seidel method and the Successive Over-Relaxation method for solving linear systems in the literature. Incorporating a new Gaussian elimination procedure, the matrix splitting method achieves state-of-the-art performance. For convex problems, we establish the global convergence, convergence rate, and iteration complexity of MSM, while for non-convex problems, we prove its global convergence. Finally, we validate the performance of our matrix splitting method on two particular applications: nonnegative matrix factorization and cardinality regularized sparse coding. Extensive experiments show that our method outperforms existing Composite Function minimization techniques in term of both efficiency and efficacy.