جستجوی مقالات مرتبط با کلیدواژه "bfgs ‎method" در نشریات گروه "ریاضی"

Location theory is an interstice field of optimization and operations research‎. ‎In the classic location models‎, ‎the goal is finding the location of one or more facilities such that some criteria such as transportation cost‎, ‎the sum of distances passed by clients‎, ‎total service time, and cost of servicing are minimized‎. ‎The goal Weber location problem is a special case of location models that have been considered recently by some researchers‎. ‎In this problem, the ideal is locating the facility in the distance $r_i$‎, ‎from the $i$-th client‎. ‎However‎, ‎in most instances‎, ‎the solution to this problem doesn't exist‎. ‎Therefore‎, ‎the minimizing sum of errors is considered‎. ‎In the previous versions of the goal location problem, the penalty functions have been considered by some symmetric functions such as square and absolute errors of distances between clients and ideal point‎. ‎In this paper‎, ‎we consider the asymmetric linex function as the error function‎. ‎We consider the case that the distances are measured by $L_p$ norm‎. ‎Some iterative methods are used to solve the problem and the results are compared with some previously examined methods.

We make some ecient modications on the modied secant equation proposed by Zhangand Xu (2001). Then we introduce modied BFGS method using propose secant equation,and obtain some attractive results in theory and practice. We establish the global con-vergence property of the proposed method without convexity assumption on the objectivefunction. Numerical results on some testing problems from CUTEr collection show the pri-ority of the proposed method to some existing modied secant methods in practice

In this paper, a novel and practical approach are proposed to solve the fuzzy optimal control (FOC) using an improved multi-layer perceptron (IMLP) network along with the Pontryagin minimum principle (PMP). Here, it is worthwhile to mention that in the fuzzy Hamilton function, instead of functions of control and trajectory and the Lagrange multipliers, the approximate solutions are replaced based on the IMLP neural network, which is a Three-layer type.

Nonlinear programming problems belong to the realm of commonly used optimization problems. In most cases, the objective function of such problems is non-convex. However, to guarantee global convergence in the algorithms proposed based on Newton's method to solve these problems, a convexity condition is generally required. Meanwhile, the quasi-Newton techniques are more popular because they use an approximation of the Hessian matrix or its inverse. However, in these algorithms, only gradient information is used to approximate this matrix. One of the most applicable quasi-Newton algorithms in solving nonlinear programming problems is the BFGS method. This paper presents a new idea for a linear search in the BFGS method. It proves that using this technique will lead to global convergence for general problems without the need for any additional conditions. Finally, the performance of the proposed algorithm is evaluated numerically.

In this paper, we introduce a hybrid approach based on neural network and optimization teqnique to solve ordinary differential equation. In proposed model we use heyperbolic secont transformation function in hiden layer of neural network part and bfgs teqnique in optimization part. In comparison with existing similar neural networks proposed model provides solutions with high accuracy. Numerical examples with simulation results illustrate the effectiveness of the proposed model.