Results 1  10
of
762,147
Optimization in Companion Search Spaces: The Case of CrossEntropy and the LevenbergMarquardt Algorithm
 in Proc. Int. Conf. Acoustics, Speech, and Signal Processing
"... We present a new learning algorithm for the supervised training of multilayer perceptrons for classification that is significantly faster than any previously known method. Like existing methods, the algorithm assumes a multilayer perceptron with a normalized exponential (softmax) output trained unde ..."
Abstract

Cited by 2 (1 self)
 Add to MetaCart
. The proposed algorithm overcomes this limitation by defining a new search space for which a secondorder expansion is valid and such that the optimal solution in the new space coincides with the original criterion. This allows the application of the LevenbergMarquardt search procedure to the crossentropy
LevenbergMarquardt Learning and Regularization
 in Progress in Neural Information Processing
, 1996
"... LevenbergMarquardt Learning was first introduced to the feedforward networks to improve the speed of the training. This method is an improved GuassNewton method which has an extra term to prevent the cases of illconditions. Interestingly, if we regard the learning as a constrained least square me ..."
Abstract

Cited by 2 (0 self)
 Add to MetaCart
by some simple modifications. In addition, with the inclusion of test for validation error, the regularization parameter can be chosen in such a way that both the training error and validation error decrease. Thus, it prevents the occurrence of overtraining. 1 Introduction LevenbergMarquardt Learning
LevenbergMarquardt Learning and Regularization
 in Progress in Neural Information Processing
, 1996
"... LevenbergMarquardt Learning was first introduced to the feedforward networks to improve the speed of the training. This method is an improved GuassNewton method which has an extra term to prevent the cases of illconditions. Interestingly, if we regard the learning as a constrained least square me ..."
Abstract
 Add to MetaCart
by some simple modifications. In addition, with the inclusion of test for validation error, the regularization parameter can be chosen in such a way that both the training error and validation error decrease. Thus, it prevents the occurrence of overtraining. 1 Introduction LevenbergMarquardt Learning
The LevenbergMarquardt Algorithm
, 2004
"... This document aims to provide an intuitive explanation for this algorithm. The LM algorithm is first shown to be a blend of vanilla gradient descent and GaussNewton iteration. Subsequently, another perspective on the algorithm is provided by considering it as a trustregion method ..."
Abstract
 Add to MetaCart
This document aims to provide an intuitive explanation for this algorithm. The LM algorithm is first shown to be a blend of vanilla gradient descent and GaussNewton iteration. Subsequently, another perspective on the algorithm is provided by considering it as a trustregion method
Levenberg–Marquardt training algorithms for random neural networks
 Comput. J
, 2011
"... Random neural networks (RNN) have been efficiently used as learning tools in many applications of different types. The learning procedure followed so far is the gradient descent one. In this paper we explore the use of the Levenberg—Marquardt (LM) optimization procedure, more powerful when it is app ..."
Abstract

Cited by 4 (1 self)
 Add to MetaCart
Random neural networks (RNN) have been efficiently used as learning tools in many applications of different types. The learning procedure followed so far is the gradient descent one. In this paper we explore the use of the Levenberg—Marquardt (LM) optimization procedure, more powerful when
An accelerated LevenbergMarquardt algorithm for feedforward network
, 2012
"... This paper proposes a new LevenbergMarquardt algorithm that is accelerated by adjusting a Jacobian matrix and a quasiHessian matrix. The proposed method partitions the Jacobian matrix into block matrices and employs the inverse of a partitioned matrix to find the inverse of the quasiHessian matr ..."
Abstract
 Add to MetaCart
This paper proposes a new LevenbergMarquardt algorithm that is accelerated by adjusting a Jacobian matrix and a quasiHessian matrix. The proposed method partitions the Jacobian matrix into block matrices and employs the inverse of a partitioned matrix to find the inverse of the quasi
A Levenberg–Marquardt method for estimating polygonal regions
, 2006
"... This article was published in an Elsevier journal. The attached copy is furnished to the author for noncommercial research and education use, including for instruction at the author’s institution, sharing with colleagues and providing to institution administration. Other uses, including reproductio ..."
Abstract
 Add to MetaCart
This article was published in an Elsevier journal. The attached copy is furnished to the author for noncommercial research and education use, including for instruction at the author’s institution, sharing with colleagues and providing to institution administration. Other uses, including reproduction and distribution, or selling or licensing copies, or posting to personal, institutional or third party websites are prohibited. In most cases authors are permitted to post their version of the article (e.g. in Word or Tex form) to their personal website or institutional repository. Authors requiring further information regarding Elsevier’s archiving and manuscript policies are encouraged to visit:
Is LevenbergMarquardt the Most Efficient Optimization Algorithm for Implementing Bundle Adjustment?
, 2005
"... In order to obtain optimal 3D structure and viewing parameter estimates, bundle adjustment is often used as the last step of featurebased structure and motion estimation algorithms. Bundle adjustment involves the formulation of a large scale, yet sparse minimization problem, which is traditionally ..."
Abstract

Cited by 34 (1 self)
 Add to MetaCart
solved using a sparse variant of the LevenbergMarquardt optimization algorithm that avoids storing and operating on zero entries. This paper argues that considerable computational benefits can be gained by substituting the sparse LevenbergMarquardt algorithm in the implementation of bundle adjustment
1 Introduction The LevenbergMarquardt Algorithm
, 2004
"... The LevenbergMarquardt (LM) algorithm is the most widely used optimization algorithm. It ..."
Abstract
 Add to MetaCart
The LevenbergMarquardt (LM) algorithm is the most widely used optimization algorithm. It
Improvements to the LevenbergMarquardt algorithm for nonlinear leastsquares minimization
"... When minimizing a nonlinear leastsquares function, the LevenbergMarquardt algorithm can suffer from a slow convergence, particularly when it must navigate a narrow canyon en route to a best fit. On the other hand, when the leastsquares function is very flat, the algorithm may easily become lost i ..."
Abstract
 Add to MetaCart
When minimizing a nonlinear leastsquares function, the LevenbergMarquardt algorithm can suffer from a slow convergence, particularly when it must navigate a narrow canyon en route to a best fit. On the other hand, when the leastsquares function is very flat, the algorithm may easily become lost
Results 1  10
of
762,147