Canonical dual solutions to nonconvex radial basis neural network optimization problem

نویسندگان

  • Vittorio Latorre
  • David Yang Gao
چکیده

Radial Basis Functions Neural Networks (RBFNNs) are tools widely used in regression problems. One of their principal drawbacks is that the formulation corresponding to the training with the supervision of both the centers and the weights is a highly non-convex optimization problem, which leads to some fundamentally difficulties for traditional optimization theory and methods. This paper presents a generalized canonical duality theory for solving this challenging problem. We demonstrate that by sequential canonical dual transformations, the nonconvex optimization problem of the RBFNN can be reformulated as a canonical dual problem (without duality gap). Both global optimal solution and local extrema can be classified. Several applications to one of the most used Radial Basis Functions, the Gaussian function, are illustrated. Our results show that even for one-dimensional case, the global minimizer of the nonconvex problem may not be the best solution to the RBFNNs, and the canonical dual theory is a promising tool for solving general neural networks training problems.

برای دانلود رایگان متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید

ثبت نام

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

منابع مشابه

Unified canonical duality methodology for global optimization

A unified methodology is presented for solving general global optimization problems. Based on the canonical dualitytriality theory, the nonconvex/nonsmooth/discrete problems from totally different systems are reformulated as a canonical min–max problem, which is equivalent to a monotone variational inequality problem over a convex cone. Therefore, a complementary-dual projection method is used ...

متن کامل

An Efficient Neurodynamic Scheme for Solving a Class of Nonconvex Nonlinear Optimization Problems

‎By p-power (or partial p-power) transformation‎, ‎the Lagrangian function in nonconvex optimization problem becomes locally convex‎. ‎In this paper‎, ‎we present a neural network based on an NCP function for solving the nonconvex optimization problem‎. An important feature of this neural network is the one-to-one correspondence between its equilibria and KKT points of the nonconvex optimizatio...

متن کامل

Solutions and optimality criteria for nonconvex quadratic-exponential minimization problem

This paper presents a set of complete solutions and optimality conditions for a nonconvex quadratic-exponential optimization problem. By using the canonical duality theory developed by the first author, the nonconvex primal problem in n-dimensional space can be converted into an one-dimensional canonical dual problem with zero duality gap, which can be solved easily to obtain all dual solutions...

متن کامل

Global optimal solutions to nonconvex optimisation problems with a sum of double-well and log-sum-exp functions

This paper presents a canonical dual approach for solving a nonconvex global optimisation problem with a sum of double-well and log-sum-exp functions. Such a problem arises extensively in mechanics, robot designing, information theory and network communication systems. It includes fourth-order polynomial minimisation problems and minimax problems. Based on the canonical duality theory, this non...

متن کامل

Solutions and optimality criteria for nonconvex constrained global optimization problems with connections between canonical and Lagrangian duality

Abstract This paper presents a canonical duality theory for solving a general nonconvex 1 quadratic minimization problem with nonconvex constraints. By using the canonical dual 2 transformation developed by the first author, the nonconvex primal problem can be con3 verted into a canonical dual problem with zero duality gap. A general analytical solution 4 form is obtained. Both global and local...

متن کامل

ذخیره در منابع من


  با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید

عنوان ژورنال:
  • Neurocomputing

دوره 134  شماره 

صفحات  -

تاریخ انتشار 2014