In this work, a recursive Levenberg-Marquardt (LM) learning algorithm in the complex domain is developed and applied to the learning of an adaptive control scheme composed by ComplexValued Recurrent Neural Networks (CVRNN). We simplified the derivation of the LM learning algorithm using a diagrammatic method to derive the adjoint CVRNN used to obtain the gradient terms. Furthermore, we apply th...

The Levenberg-Marquardt (LM) algorithm is an iterative technique that locates the minimum of a function that is expressed as the sum of squares of nonlinear functions. It has become a standard technique for nonlinear least-squares problems and can be thought of as a combination of steepest descent and the Gauss-Newton method. This document briefly describes the mathematics behind levmar, a free...

We present an approach based on the improved Levenberg Marquardt (LM) algorithm of backpropagation (BP) neural network to estimate the light source position in bioluminescent imaging. For solving the forward problem, the table-based random sampling algorithm (TBRS), a fast Monte Carlo simulation method we developed before, is employed here. Result shows that BP is an effective method to positio...

We compare algorithms for fundamental matrix computation, which we classify into “a posteriori correction”, “internal access”, and “external access”. Doing experimental comparison, we show that the 7-parameter Levenberg-Marquardt (LM) search and the extended FNS (EFNS) exhibit the best performance and that additional bundle adjustment does not increase the accuracy to any noticeable degree.

recently, hardware sensors are widely used in monitoring and measurement of water quality parameters. constraint of the instrument to measure some water quality parameters such as the 5-day biochemical oxygen demand (bod5), which are time consuming, causes efforts are diverted to the use of software sensors for online prediction of bod5. the main goal of this research is developing an appropria...

The purpose of this study was to compare the performance of two methods for gravity inversion of a fault. First method [Particle swarm optimization (PSO)] is a heuristic global optimization method and also an optimization algorithm, which is based on swarm intelligence. It comes from the research on the bird and fish flock movement behavior. Second method [The Levenberg-Marquardt algorithm (LM)...

The improved computation presented in this paper is aimed to optimize the neural networks learning process using Levenberg-Marquardt (LM) algorithm. Quasi-Hessian matrix and gradient vector are computed directly, without Jacobian matrix multiplication and storage. The memory limitation problem for LM training is solved. Considering the symmetry of quasi-Hessian matrix, only elements in its uppe...

The Levenberg-Marquardt (LM) learning algorithm is a popular algorithm for training neural networks; however, for large neural networks, it becomes prohibitively expensive in terms of running time and memory requirements. The most time-critical step of the algorithm is the calculation of the Gauss-Newton matrix, which is formed by multiplying two large Jacobian matrices together. We propose a m...

This paper makes two principal contributions. The first is that there appears to be no previous a description in the research literature of an artificial neural network implementation on a graphics processor unit (GPU) that uses the Levenberg-Marquardt (LM) training method. The second is an initial attempt at determining when it is computationally beneficial to exploit a GPU’s parallel nature i...

A new adaptive hybrid optimization strategy, entitled squads, is proposed for complex inverse analysis of computationally intensive physics-based models. Typically, models are calibrated and model parameters are estimated by minimization of the discrepancy between model simulations characterizing the system and existing observations requiring a substantial number of model evaluations. Squads is...